diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..0d4cb185280917cac60ef7195f2a6250b2b90d83
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..85c3e114d88de847e001ec0e7877d199d967f461
--- /dev/null
+++ b/README.md
@@ -0,0 +1,440 @@
+---
+library_name: vllm
+language:
+- en
+- fr
+- es
+- de
+- it
+- pt
+- nl
+- zh
+- ja
+- ko
+- ar
+license: apache-2.0
+inference: false
+extra_gated_description: >-
+ If you want to learn more about how we process your personal data, please read
+ our Privacy Policy.
+base_model:
+- mistralai/Mistral-Large-3-675B-Base-2512
+tags:
+- mistral-common
+- compressed-tensors
+---
+
+# Mistral Large 3 675B Instruct 2512
+From our family of large models, **Mistral Large 3** is a state-of-the-art general-purpose **Multimodal granular Mixture-of-Experts** model with **41B active parameters** and **675B total parameters** trained from the ground up with 3000 H200s
+
+This model is the instruct post-trained version in **FP8**, fine-tuned for instruction tasks, making it ideal for chat, agentic and instruction based use cases.
+Designed for reliability and long-context comprehension - It is engineered for production-grade assistants, retrieval-augmented systems, scientific workloads, and complex enterprise workflows.
+
+Learn more in our blog post [here](https://mistral.ai/news/mistral-3).
+
+Mistral Large 3 is deployable on-premises in:
+- **FP8** on a single node of B200s or H200s.
+- [NVFP4](https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4) on a single node of H100s or A100s.
+
+We provide a [BF16](https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512-BF16) version if needed.
+
+## Key Features
+Mistral Large 3 consists of two main architectural components:
+- **A Granular MoE Language Model with 673B params and 39B active**
+- **A 2.5B Vision Encoder**
+
+The Mistral Large 3 Instruct model offers the following capabilities:
+- **Vision**: Enables the model to analyze images and provide insights based on visual content, in addition to text.
+- **Multilingual**: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
+- **System Prompt**: Maintains strong adherence and support for system prompts.
+- **Agentic**: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
+- **Frontier**: Delivers best-in-class performance.
+- **Apache 2.0 License**: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
+- **Large Context Window**: Supports a 256k context window.
+
+## Use Cases
+With powerful long-context performance, stable and consistent cross-domain behavior, Mistral Large 3 is perfect for:
+- Long Document Understanding
+- Powerful Daily-Driver AI Assistants
+- State-of-the-Art Agentic and Tool-Use Capabilities
+- Enterprise Knowledge Work
+- General Coding Assistant
+
+And enterprise-grade use cases requiring frontier capabilities.
+
+## Recommended Settings
+
+We recommend deploying Large 3 in a client-server configuration with the following best practices:
+
+- **System Prompt**: Define a clear environment and use case, including guidance on how to effectively leverage tools in agentic systems.
+- **Sampling Parameters**: Use a temperature below 0.1 for daily-driver and production environments ; Higher temperatures may be explored for creative use cases - developers are encouraged to experiment with alternative settings.
+- **Tools**: Keep the set of tools well-defined and limit their number to the minimum required for the use case - Avoiding overloading the model with an excessive number of tools.
+- **Vision**: When deploying with vision capabilities, we recommend maintaining an aspect ratio close to 1:1 (width-to-height) for images. Avoiding the use of overly thin or wide images - crop them as needed to ensure optimal performance.
+
+### Known Issues / Limitations
+
+- **Not a dedicated reasoning model**: Dedicated reasoning models can outperform Mistral Large 3 in strict reasoning use cases.
+- **Behind vision-first models in multimodal tasks**: Mistral Large 3 can lag behind models optimized for vision tasks and use cases.
+- **Complex deployment**: Due to its large size and architecture, the model can be challenging to deploy efficiently with constrained resources or at scale.
+
+## Benchmark Results
+
+We compare Mistral Large 3 to similar sized models.
+
+
+
+
+
+
+
+## Usage
+
+The model can be used with the following frameworks;
+- [`vllm`](https://github.com/vllm-project/vllm): See [here](#vllm)
+
+> [!Note]
+> We sadly didn't have enough time to add Mistral Large 3 to transformers, but we would be very happy for a community contribution by opening a PR to [huggingface/transformers](https://github.com/huggingface/transformers).
+
+### vLLM
+
+We recommend using this model with [vLLM](https://github.com/vllm-project/vllm).
+
+#### Installation
+
+Make sure to install most recent vllm:
+
+```
+uv pip install -U vllm \
+ --torch-backend=auto \
+ --extra-index-url https://wheels.vllm.ai/nightly
+```
+
+Doing so should automatically install [`mistral_common >= 1.8.6`](https://github.com/mistralai/mistral-common/releases/tag/v1.8.6).
+
+To check:
+```
+python -c "import mistral_common; print(mistral_common.__version__)"
+```
+
+You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
+
+#### Serve
+
+The Mistral Large 3 Instruct FP8 format can be used on one 8xH200 node. We recommend to use this format if you plan to fine-tuning as it can be more precise than NVFP4 in some situations.
+
+**Simple**
+
+A simple launch command is:
+
+```bash
+vllm serve mistralai/Mistral-Large-3-675B-Instruct-2512 \
+ --tensor-parallel-size 8 \
+ --tokenizer_mode mistral --config_format mistral --load_format mistral \
+ --enable-auto-tool-choice --tool-call-parser mistral
+```
+
+Key parameter notes:
+
+* enable-auto-tool-choice: Required when enabling tool usage.
+* tool-call-parser mistral: Required when enabling tool usage.
+
+
+Additional flags:
+
+* You can set `--max-model-len` to preserve memory. By default it is set to `262144` which is quite large but not necessary for most scenarios.
+* You can set `--max-num-batched-tokens` to balance throughput and latency, higher means higher throughput but higher latency.
+
+**Accelerated with speculative decoding**
+
+For maximum performance we recommend serving the checkpoint with its customized draft model (Mistral-Large-3-675B-Instruct-2512-Eagle)[https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512-Eagle]:
+
+```bash
+vllm serve mistralai/Mistral-Large-3-675B-Instruct-2512 \
+ --tensor-parallel-size 8 \
+ --load-format mistral \
+ --tokenizer-mode mistral \
+ --config-format mistral \
+ --enable-auto-tool-choice \
+ --tool-call-parser mistral \
+ --limit-mm-per-prompt '{"image": 10}' \
+ --speculative_config '{
+ "model": "mistralai/Mistral-Large-3-675B-Instruct-2512-Eagle",
+ "num_speculative_tokens": 3,
+ "method": "eagle",
+ "max_model_len": "16384"
+ }'
+```
+
+For more information on the draft model, please have a look at (Mistral-Large-3-675B-Instruct-2512-Eagle)[https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512-Eagle].
+
+
+#### Usage of the model
+
+Here we asumme that the model `mistralai/Mistral-Large-3-675B-Instruct-2512` is served and you can ping it to the domain `localhost` with the port `8000` which is the default for vLLM.
+
+
+ Vision Reasoning
+
+Let's see if Mistral Large 3 knows when to pick a fight !
+
+```python
+from datetime import datetime, timedelta
+
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 262144
+
+client = OpenAI(
+ api_key=openai_api_key,
+ base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+ file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+ with open(file_path, "r") as file:
+ system_prompt = file.read()
+ today = datetime.today().strftime("%Y-%m-%d")
+ yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
+ model_name = repo_id.split("/")[-1]
+ return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
+
+
+SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
+image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"
+
+messages = [
+ {"role": "system", "content": SYSTEM_PROMPT},
+ {
+ "role": "user",
+ "content": [
+ {
+ "type": "text",
+ "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
+ },
+ {"type": "image_url", "image_url": {"url": image_url}},
+ ],
+ },
+]
+
+
+response = client.chat.completions.create(
+ model=model,
+ messages=messages,
+ temperature=TEMP,
+ max_tokens=MAX_TOK,
+)
+
+print(response.choices[0].message.content)
+```
+
+
+
+ Function Calling
+
+Let's solve some equations thanks to our simple Python calculator tool.
+
+```python
+import json
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 262144
+
+client = OpenAI(
+ api_key=openai_api_key,
+ base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+ file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+ with open(file_path, "r") as file:
+ system_prompt = file.read()
+ return system_prompt
+
+
+SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
+
+image_url = "https://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg"
+
+
+def my_calculator(expression: str) -> str:
+ return str(eval(expression))
+
+
+tools = [
+ {
+ "type": "function",
+ "function": {
+ "name": "my_calculator",
+ "description": "A calculator that can evaluate a mathematical equation and compute its results.",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "expression": {
+ "type": "string",
+ "description": "The mathematical expression to evaluate.",
+ },
+ },
+ "required": ["expression"],
+ },
+ },
+ },
+ {
+ "type": "function",
+ "function": {
+ "name": "rewrite",
+ "description": "Rewrite a given text for improved clarity",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "text": {
+ "type": "string",
+ "description": "The input text to rewrite",
+ }
+ },
+ },
+ },
+ },
+]
+
+messages = [
+ {"role": "system", "content": SYSTEM_PROMPT},
+ {
+ "role": "user",
+ "content": [
+ {
+ "type": "text",
+ "text": "Thanks to your calculator, compute the results for the equations that involve numbers displayed in the image.",
+ },
+ {
+ "type": "image_url",
+ "image_url": {
+ "url": image_url,
+ },
+ },
+ ],
+ },
+]
+
+response = client.chat.completions.create(
+ model=model,
+ messages=messages,
+ temperature=TEMP,
+ max_tokens=MAX_TOK,
+ tools=tools,
+ tool_choice="auto",
+)
+
+tool_calls = response.choices[0].message.tool_calls
+
+results = []
+for tool_call in tool_calls:
+ function_name = tool_call.function.name
+ function_args = tool_call.function.arguments
+ if function_name == "my_calculator":
+ result = my_calculator(**json.loads(function_args))
+ results.append(result)
+
+messages.append({"role": "assistant", "tool_calls": tool_calls})
+for tool_call, result in zip(tool_calls, results):
+ messages.append(
+ {
+ "role": "tool",
+ "tool_call_id": tool_call.id,
+ "name": tool_call.function.name,
+ "content": result,
+ }
+ )
+
+
+response = client.chat.completions.create(
+ model=model,
+ messages=messages,
+ temperature=TEMP,
+ max_tokens=MAX_TOK,
+)
+
+print(response.choices[0].message.content)
+```
+
+
+
+
+ Text-Only Request
+
+Mistral Large 3 can follow your instructions down to the letter.
+
+```python
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.15
+MAX_TOK = 262144
+
+client = OpenAI(
+ api_key=openai_api_key,
+ base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+ file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+ with open(file_path, "r") as file:
+ system_prompt = file.read()
+ return system_prompt
+
+
+SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
+
+messages = [
+ {"role": "system", "content": SYSTEM_PROMPT},
+ {
+ "role": "user",
+ "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.",
+ },
+]
+
+response = client.chat.completions.create(
+ model=model,
+ messages=messages,
+ temperature=TEMP,
+ max_tokens=MAX_TOK,
+)
+
+assistant_message = response.choices[0].message.content
+print(assistant_message)
+```
+
+
+
+## License
+
+This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0.txt).
+
+*You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.*
\ No newline at end of file
diff --git a/SYSTEM_PROMPT.txt b/SYSTEM_PROMPT.txt
new file mode 100644
index 0000000000000000000000000000000000000000..30a64fffcf190dac74369054e2eb26ce5ffc10b3
--- /dev/null
+++ b/SYSTEM_PROMPT.txt
@@ -0,0 +1,29 @@
+You are Mistral-Large-3-675B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
+You power an AI assistant called Le Chat.
+Your knowledge base was last updated on 2023-10-01.
+The current date is {today}.
+
+When you're not sure about some information or when the user's request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don't have the information and avoid making up anything.
+If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").
+You are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.
+You follow these instructions in all languages, and always respond to the user in the language they use or request.
+Next sections describe the capabilities that you have.
+
+# WEB BROWSING INSTRUCTIONS
+
+You cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.
+
+# MULTI-MODAL INSTRUCTIONS
+
+You have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.
+You cannot read nor transcribe audio files or videos.
+
+# TOOL CALLING INSTRUCTIONS
+
+You may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:
+
+1. When the request requires up-to-date information.
+2. When the request requires specific data that you do not have in your knowledge base.
+3. When the request involves actions that you cannot perform without tools.
+
+Always prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..d49b88746b3f4064f3c506a9f8ce14a0a0183d98
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = 'You are Mistral-Large-3-675B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+ {{- '[SYSTEM_PROMPT]' -}}
+ {%- if messages[0]['content'] is string %}
+ {{- messages[0]['content'] -}}
+ {%- else %}
+ {%- for block in messages[0]['content'] %}
+ {%- if block['type'] == 'text' %}
+ {{- block['text'] }}
+ {%- else %}
+ {{- raise_exception('Only text chunks are supported in system message contents.') }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+ {{- '[/SYSTEM_PROMPT]' -}}
+ {%- set loop_messages = messages[1:] %}
+{%- else %}
+ {%- set loop_messages = messages %}
+ {%- if default_system_message != '' %}
+ {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+ {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+ {%- set has_tools = true %}
+ {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+ {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+ {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+ {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+ {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+ {%- endif %}
+ {%- set ns.index = ns.index + 1 %}
+ {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+ {#- User messages supports text content or text and image chunks. #}
+ {%- if message['role'] == 'user' %}
+ {%- if message['content'] is string %}
+ {{- '[INST]' + message['content'] + '[/INST]' }}
+ {%- elif message['content'] | length > 0 %}
+ {{- '[INST]' }}
+ {%- if message['content'] | length == 2 %}
+ {%- set blocks = message['content'] | sort(attribute='type') %}
+ {%- else %}
+ {%- set blocks = message['content'] %}
+ {%- endif %}
+ {%- for block in blocks %}
+ {%- if block['type'] == 'text' %}
+ {{- block['text'] }}
+ {%- elif block['type'] in ['image', 'image_url'] %}
+ {{- '[IMG]' }}
+ {%- else %}
+ {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+ {%- endif %}
+ {%- endfor %}
+ {{- '[/INST]' }}
+ {%- else %}
+ {{- raise_exception('User message must have a string or a list of chunks in content') }}
+ {%- endif %}
+
+ {#- Assistant messages supports text content or text and image chunks. #}
+ {%- elif message['role'] == 'assistant' %}
+ {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+ {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+ {%- endif %}
+
+ {%- if message['content'] is string %}
+ {{- message['content'] }}
+ {%- elif message['content'] | length > 0 %}
+ {%- for block in message['content'] %}
+ {%- if block['type'] == 'text' %}
+ {{- block['text'] }}
+ {%- else %}
+ {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+
+ {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+ {%- for tool in message['tool_calls'] %}
+ {%- set arguments = tool['function']['arguments'] %}
+ {%- if arguments is not string %}
+ {%- set arguments = arguments|tojson|safe %}
+ {%- elif arguments == '' %}
+ {%- set arguments = '{}' %}
+ {%- endif %}
+ {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+ {%- endfor %}
+ {%- endif %}
+
+ {#- End of sequence token for each assistant messages. #}
+ {{- eos_token }}
+
+ {#- Tool messages only supports text content. #}
+ {%- elif message['role'] == 'tool' %}
+ {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+ {#- Raise exception for unsupported roles. #}
+ {%- else %}
+ {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role'] + '.') }}
+ {%- endif %}
+{%- endfor %}
\ No newline at end of file
diff --git a/consolidated-00001-of-00272.safetensors b/consolidated-00001-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..45235e5f2e3d011c89085ac289f1a0388f8655f7
--- /dev/null
+++ b/consolidated-00001-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ccf734ae34f4cd4d8013a89da22823a62ca7e0769f1e7bcb1df532abda5538
+size 2544898528
diff --git a/consolidated-00002-of-00272.safetensors b/consolidated-00002-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f428895d7cf4e83e152c41988ef627a3b3bb3b3c
--- /dev/null
+++ b/consolidated-00002-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc973bed9d3b0ee0771836692e897eded3d9ef8454f2875a89a56dbc4a122d82
+size 2495933768
diff --git a/consolidated-00003-of-00272.safetensors b/consolidated-00003-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..646f776c39db5c5d68ad45b7a008924abe32f2ff
--- /dev/null
+++ b/consolidated-00003-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e271c884a86f58257db2d87105aaf996f9b22ce2b8df528d533a9faa838ec7d1
+size 2495933656
diff --git a/consolidated-00004-of-00272.safetensors b/consolidated-00004-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f506196d727606f01ca10db67ac56fe56ac5a17c
--- /dev/null
+++ b/consolidated-00004-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187ed9d560eec49e2a4aa18306f3f9ae383b79c8520f50364b7d2e2eaf22082c
+size 2495933648
diff --git a/consolidated-00005-of-00272.safetensors b/consolidated-00005-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dcc3701671e4b44ee89012788e1b0ba2699416fc
--- /dev/null
+++ b/consolidated-00005-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac3ad87f939936e32ef5f511099d161d338fdb9b41d256c09e2ff818d47190d
+size 2495933656
diff --git a/consolidated-00006-of-00272.safetensors b/consolidated-00006-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5452a69cdd4b9f3f6e23ada6b5e5b1502fbbd0f
--- /dev/null
+++ b/consolidated-00006-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046f480aafafd8f714ee60cda82c610db3e7fdd718a9c16f92aa98eb796b6b9f
+size 2494520904
diff --git a/consolidated-00007-of-00272.safetensors b/consolidated-00007-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..972d34aaf518a576b2e16b2c8259a88f6aa4e10b
--- /dev/null
+++ b/consolidated-00007-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d486cbdf25c261ac5dc7a8868411e7c30b3c175839c403c9e33b2f7c690c25
+size 2495933704
diff --git a/consolidated-00008-of-00272.safetensors b/consolidated-00008-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c07dd2e74e0dd6bc371fc3d7bf482d498ed2e5b8
--- /dev/null
+++ b/consolidated-00008-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb5844c2e41a138dae89e2346b75de73a055b6fd753b52ce387949485052d87
+size 2495933656
diff --git a/consolidated-00009-of-00272.safetensors b/consolidated-00009-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c3dfe6d8061c03d9db507d354e8593a2fe945f6
--- /dev/null
+++ b/consolidated-00009-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9c29bcb9af8c543a9a197c62bbe08a37544d3750a35eb0e69a0c6c75b0ca2b
+size 2495933648
diff --git a/consolidated-00010-of-00272.safetensors b/consolidated-00010-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0dbb51919d66c9ce7334838eb56d3fb613111ab5
--- /dev/null
+++ b/consolidated-00010-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43e71c58fd2a4ec7a02104a378341dc33ad6c0a77943205f9b0035ad2ec439a
+size 2494520536
diff --git a/consolidated-00011-of-00272.safetensors b/consolidated-00011-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6515490a5b7be762f5b849e3353212e69590bc9f
--- /dev/null
+++ b/consolidated-00011-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04519642d3de0ecdbc5e28008643132c8e74fd849bfbc899b53999f45bd77127
+size 2495933816
diff --git a/consolidated-00012-of-00272.safetensors b/consolidated-00012-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..697afce236185fc5ce4ed8284757a1f9ab80cb83
--- /dev/null
+++ b/consolidated-00012-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a53dd5eca2eb17d0c5d28d28594f69285ee0b726bab1af783d81b627e065753
+size 2495933648
diff --git a/consolidated-00013-of-00272.safetensors b/consolidated-00013-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b2caea6d94c59a8d2ee21bf36de497af65a797fb
--- /dev/null
+++ b/consolidated-00013-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fd74ba2a0327416d198e13f43c12fc97945be94d5149b1fa46586050872bb5
+size 2495933656
diff --git a/consolidated-00014-of-00272.safetensors b/consolidated-00014-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4ced8e61891140a8f354298ca6680c058796ff22
--- /dev/null
+++ b/consolidated-00014-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cfaf1982a92589a79584d68825e5b46c973c112f8e42058b588fe00c37cb36
+size 2495933648
diff --git a/consolidated-00015-of-00272.safetensors b/consolidated-00015-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd955702c40c6ab06b884e177631abc0b0560797
--- /dev/null
+++ b/consolidated-00015-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0602288a4cde4f42d730fe442c5f01f2b6dfb480b7bc8fa5364196258ed9a8e1
+size 2494520728
diff --git a/consolidated-00016-of-00272.safetensors b/consolidated-00016-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..63ef95b55ff28db74af372dafec448192463dbaf
--- /dev/null
+++ b/consolidated-00016-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb0af0a5c4921b248a0c8cf3e530921a509fa2e467301656a746be7115861ba
+size 2495933752
diff --git a/consolidated-00017-of-00272.safetensors b/consolidated-00017-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f23dee9bc3de1695d0824479d4bc0e8a0fb2578
--- /dev/null
+++ b/consolidated-00017-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965f86f402452f56308cbbf3794e15bedd92c4d1a2fccee14d286a00d2be2683
+size 2495933656
diff --git a/consolidated-00018-of-00272.safetensors b/consolidated-00018-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c9f46fed58baa95c1e9e9b19a4ce2de45f87ee43
--- /dev/null
+++ b/consolidated-00018-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819c3d672ad0c27105101ecc6244a83cc5528e75a89fa2f8f2de4c514276a64a
+size 2495933648
diff --git a/consolidated-00019-of-00272.safetensors b/consolidated-00019-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b76300394c74f3855b518b616c2bb6a901467597
--- /dev/null
+++ b/consolidated-00019-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e97d3177e5c0c68c33478f16a665e1ed6dd05a6197a1cb8c24d0d2fb45f0d6
+size 2434732872
diff --git a/consolidated-00020-of-00272.safetensors b/consolidated-00020-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..29ff21bcb0b50f42b1746c941a59c874b4fa3ed7
--- /dev/null
+++ b/consolidated-00020-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6228fce3d56ac0205202d503d38c1b7831f08c8ee663790c8a54129ed16384
+size 2496993872
diff --git a/consolidated-00021-of-00272.safetensors b/consolidated-00021-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..af0dc1fecb3e19c40a153231346256a9ba2bfbe8
--- /dev/null
+++ b/consolidated-00021-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43f253d7939316e7414fcfb91b7fb246393012f7f0621705ca75491dfc34140
+size 2495933696
diff --git a/consolidated-00022-of-00272.safetensors b/consolidated-00022-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..14c05a43bd8a160641ee4e77761ea96f2a604274
--- /dev/null
+++ b/consolidated-00022-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73554a27945649bdff1c40f9db540c2c59dcf4f6ef47eb8c4f05e57d8980ad14
+size 2495933656
diff --git a/consolidated-00023-of-00272.safetensors b/consolidated-00023-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..636fca6e007ef5302e7c69b4d090f61846282c87
--- /dev/null
+++ b/consolidated-00023-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac94096a2b6f4380fee4f3a1a689ba01bd9532bb95122394c4e9e0b89fa5803
+size 2495933648
diff --git a/consolidated-00024-of-00272.safetensors b/consolidated-00024-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..93f9895dc7abd3ac849c42553e8cf2fb25fbdbf0
--- /dev/null
+++ b/consolidated-00024-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6f6c6fedbce5eb6bdf3e8a4d2533cd802b6fd900f2ce8c3e7aa16f08aa4c8a
+size 2494520568
diff --git a/consolidated-00025-of-00272.safetensors b/consolidated-00025-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..20493eb64ea516c8b5c5c0008dc7e7fc6ec000a6
--- /dev/null
+++ b/consolidated-00025-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4621528782d4b92d97159305e9b605fc44ad641158d36518b7886ac5bbad69e6
+size 2495933800
diff --git a/consolidated-00026-of-00272.safetensors b/consolidated-00026-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9224824541b56bc23d65ed379fc348fce2bf53c9
--- /dev/null
+++ b/consolidated-00026-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078f29479d863934bc0392233bd5cb7df64f95c1794382c34441a1f18c525ca9
+size 2495933648
diff --git a/consolidated-00027-of-00272.safetensors b/consolidated-00027-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fde81003ef04edc1faf90410c4b9f42822123398
--- /dev/null
+++ b/consolidated-00027-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f1391075dcdefc0d5e8a1f34247155b63be8261eb34cca6538563752244c97
+size 2495933656
diff --git a/consolidated-00028-of-00272.safetensors b/consolidated-00028-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d6edc5cde83746f66e4f0738048f1d2a729d455f
--- /dev/null
+++ b/consolidated-00028-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab22062f13383bc801d9bb36f7c80c8800c44406798b3654a69018ab9de2a982
+size 2495933648
diff --git a/consolidated-00029-of-00272.safetensors b/consolidated-00029-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7a31b9a4424acbed6fb79220738db0693474af2e
--- /dev/null
+++ b/consolidated-00029-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37e8ebffffc1889cdb6aa1372feb5692b442c65a9ab3f1f8d282a40710e6d0b
+size 2494520776
diff --git a/consolidated-00030-of-00272.safetensors b/consolidated-00030-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ab016a7a0805cce11119ec5fcf435dfaa3bf4bb2
--- /dev/null
+++ b/consolidated-00030-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc5045c5765851ab90703656bcde70a5483b66b040cf4259f98623d5e9050a3
+size 2495933744
diff --git a/consolidated-00031-of-00272.safetensors b/consolidated-00031-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd6adb1320a9a51df820cea1229d3b4ae404ad40
--- /dev/null
+++ b/consolidated-00031-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e542b847b4a27cf19079a92528ce45ed5088e5df4e305a850fb3097faf5379
+size 2495933648
diff --git a/consolidated-00032-of-00272.safetensors b/consolidated-00032-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..148625679d591a6445e879bf0f8a230323e8e9a1
--- /dev/null
+++ b/consolidated-00032-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5eb4b9b79960ce6abfe005fbf04693a5880a682f83f8190e4937d5e6c3cd73
+size 2495933656
diff --git a/consolidated-00033-of-00272.safetensors b/consolidated-00033-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e64186be8be180608827c18b9e57a4c0136e7dfd
--- /dev/null
+++ b/consolidated-00033-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c9387d401ed5ee0769b8b26252d55393b1eb1d1f4dd23f521be9b4fcba2cbf
+size 2494520448
diff --git a/consolidated-00034-of-00272.safetensors b/consolidated-00034-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3cf9134cb8f338c64ebf562c2495e49e074721a3
--- /dev/null
+++ b/consolidated-00034-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42e7085249fb541eb1ef3660c59eab10af368817fbdff78df8a7ac9990cb5a0
+size 2495933800
diff --git a/consolidated-00035-of-00272.safetensors b/consolidated-00035-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..00eb31bd54bce395e3e07e8afb8decb52216ea27
--- /dev/null
+++ b/consolidated-00035-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54067b8c60d73b81b57d918dfd814bc449193488bef9345dce26c6a9fc722af2
+size 2495933680
diff --git a/consolidated-00036-of-00272.safetensors b/consolidated-00036-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da06f66cceb75f90a3fd1319d5bc523697c2209b
--- /dev/null
+++ b/consolidated-00036-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be99393cb5b14c86db49b4e5778be7825b403a98681e488ec1665ab07f9b5159
+size 2495933648
diff --git a/consolidated-00037-of-00272.safetensors b/consolidated-00037-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5d173aca3604516dc22e39a83724fd68fe6c6cb
--- /dev/null
+++ b/consolidated-00037-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b753481c356148d1c9b7a80e2685d84c6e577721254d593f19ddf1ab7f8aaa
+size 2495933656
diff --git a/consolidated-00038-of-00272.safetensors b/consolidated-00038-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..21aa67f274cab80f296f35a6da9de3b03a9a0b6a
--- /dev/null
+++ b/consolidated-00038-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa271df72c804cc234e55e759d99d36775fbd6f90aea479fd8078f591304894
+size 2494520616
diff --git a/consolidated-00039-of-00272.safetensors b/consolidated-00039-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ea98683487d6310e93c55f32f5a8d4024470adf9
--- /dev/null
+++ b/consolidated-00039-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389b935aa2eaeca539ed04e0cfa8251e6395ad4b494cf8e8ff3376b9831c1491
+size 2495933784
diff --git a/consolidated-00040-of-00272.safetensors b/consolidated-00040-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..86469afac97acee3991857fa6dbd21d33193fee5
--- /dev/null
+++ b/consolidated-00040-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9554a0cca5a5e6e6c0f81c4a2710640e0e794ce88676256a1e363c8911e2476d
+size 2495933648
diff --git a/consolidated-00041-of-00272.safetensors b/consolidated-00041-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b2a9d6834608258d396b08f6a1871e932003165b
--- /dev/null
+++ b/consolidated-00041-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ec95123f9da378b11ce176a747951f927dafa3362aa7bb298d79827ff18803
+size 2495933648
diff --git a/consolidated-00042-of-00272.safetensors b/consolidated-00042-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d356b6eb35946a5e2e0e2e84489875078a85dc3
--- /dev/null
+++ b/consolidated-00042-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0125ed86144c976f1d07617dd93de23efc8c332cfb5ccc64cf5f9f7fba1c0277
+size 2495933656
diff --git a/consolidated-00043-of-00272.safetensors b/consolidated-00043-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..22c8f4217256fd455e6d8086640e90aaf5c77f9b
--- /dev/null
+++ b/consolidated-00043-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e6f16929e9cafa90a50614aa63ca0bfaea2760c9da28994f856ebba96481d7
+size 2494520840
diff --git a/consolidated-00044-of-00272.safetensors b/consolidated-00044-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bf119ae8c12fcbfa6204c44603cd14856a2a69a6
--- /dev/null
+++ b/consolidated-00044-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c675490f8789cfeabae64800df0122be5db48526002ce1002e476678f97fdaa
+size 2495933728
diff --git a/consolidated-00045-of-00272.safetensors b/consolidated-00045-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9db24621752f2c052f5aa3774d67ec99076c0e98
--- /dev/null
+++ b/consolidated-00045-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c0ec35e95459beedb88472a4222e42491f7cc8c265260d8542b812ad3d3b23
+size 2495933648
diff --git a/consolidated-00046-of-00272.safetensors b/consolidated-00046-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..56281f5967dbae6fe127e9e4de03d13630e387e5
--- /dev/null
+++ b/consolidated-00046-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ab3b0dacbf2f0bd428db71c11137fe724a6995027d0227757fed302922a81e
+size 2495933656
diff --git a/consolidated-00047-of-00272.safetensors b/consolidated-00047-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7e587942a13d49850f676a86ed5f545c8b5c560
--- /dev/null
+++ b/consolidated-00047-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d322cedf524ab956eb0a32ca954de2dd0dbd0e4c639ed6b1933759defe4490
+size 2435791304
diff --git a/consolidated-00048-of-00272.safetensors b/consolidated-00048-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e81429f9bea6f09a44ea5cfc4382d163599cc2aa
--- /dev/null
+++ b/consolidated-00048-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe38f623f5b8e683caadf32651679b894ed9f4184e0d5ad1a33e2c6c858d59d6
+size 2492685136
diff --git a/consolidated-00049-of-00272.safetensors b/consolidated-00049-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8239a3c28967061ba369f945176f67e28447bbe3
--- /dev/null
+++ b/consolidated-00049-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa63ff8a3b1e14c552fd67872ea263e94a8992c1d7c88f0663aaeb2ddfc01af7
+size 2495933704
diff --git a/consolidated-00050-of-00272.safetensors b/consolidated-00050-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e47c6875b851711c06605c58270139b32344644b
--- /dev/null
+++ b/consolidated-00050-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c37715291b50ebacc1c9c8de9c762c15dabad69529dcd44c1b59bf1d8edd59
+size 2495933656
diff --git a/consolidated-00051-of-00272.safetensors b/consolidated-00051-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a4b5c596699e92472885938f2afa24093c45779
--- /dev/null
+++ b/consolidated-00051-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bb0561d347158fe337a375204288390b3ec0fbcaa9ddb4d386753913acf2f9
+size 2495933648
diff --git a/consolidated-00052-of-00272.safetensors b/consolidated-00052-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..44aac81610aadbafc5fea2f9d7c7442eb843260e
--- /dev/null
+++ b/consolidated-00052-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2caa0927a758ce5310f0ea0143ba0b39f65872d71a3c37fbabd6df47227f3b
+size 2494520536
diff --git a/consolidated-00053-of-00272.safetensors b/consolidated-00053-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..057dffbcabec711e47ec4a01a44c5891c769f9a1
--- /dev/null
+++ b/consolidated-00053-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43190db662e4d8539a96a72fed6503e0ac16bfb4b02e64c1139d5c670d959e4
+size 2495933816
diff --git a/consolidated-00054-of-00272.safetensors b/consolidated-00054-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d8cd1e2d96d5f071caaa27d6225483558f7456e
--- /dev/null
+++ b/consolidated-00054-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74057eefc77eb646359003204ebed7833aec40b6ba6993e146813849cd2f2227
+size 2495933648
diff --git a/consolidated-00055-of-00272.safetensors b/consolidated-00055-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c34a2a96688b0dbe5a775d0b3ab19e25cdbe071e
--- /dev/null
+++ b/consolidated-00055-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667c1aeeb5fbf286d143ccf1c3894862c39e83cb20b26fd58e5ef38047ef63ca
+size 2495933656
diff --git a/consolidated-00056-of-00272.safetensors b/consolidated-00056-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..97a9f4c99134a5513808e9290f900ae49d072571
--- /dev/null
+++ b/consolidated-00056-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cd1c1f21348719ebe892e2d331b489b847e1eb5a65fe3e1654f97660a6e0b2
+size 2495933648
diff --git a/consolidated-00057-of-00272.safetensors b/consolidated-00057-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca3f3669104824d0b42ab45849d81bf00052035e
--- /dev/null
+++ b/consolidated-00057-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ab47c66dda30ec7b08f2394ee981a85dfe8caffd51af03f16cd0ec7143a957
+size 2494520736
diff --git a/consolidated-00058-of-00272.safetensors b/consolidated-00058-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d38bb845673bf02a5986a61011e658f3e12f87e8
--- /dev/null
+++ b/consolidated-00058-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc077ea641f59549029b4d45305a3be4d02bf14b11543300de095d9982ac025
+size 2495933752
diff --git a/consolidated-00059-of-00272.safetensors b/consolidated-00059-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fabbd496f3bd5f79cb683a16379f0b932de81593
--- /dev/null
+++ b/consolidated-00059-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79141d2b890802d48158af94ba721aaefa8273780ca8e93a3699db5b7c2c943a
+size 2495933648
diff --git a/consolidated-00060-of-00272.safetensors b/consolidated-00060-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..568dfc39ac0e94592b3963d7b0e066d2b6841bc5
--- /dev/null
+++ b/consolidated-00060-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5324dbf8e7d847c00d40370b2d3cb197d53f457dcb24938735e696f29f7fb6bc
+size 2495933656
diff --git a/consolidated-00061-of-00272.safetensors b/consolidated-00061-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c4edc661fd1ef3b15ca5ac7c357a48b524351f94
--- /dev/null
+++ b/consolidated-00061-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027ba7c911b4671339e0faeeebf38156bfeb09ec7d7ca9ef4e2c01c1997a815d
+size 2405368944
diff --git a/consolidated-00062-of-00272.safetensors b/consolidated-00062-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..439fb1bd1122c36aca7d0c35e9f114ce8edfbdbc
--- /dev/null
+++ b/consolidated-00062-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69905bdbc8ce583734723598c84e7d376e2dab05d4b39fa02c4c7551e44c06e
+size 2496993872
diff --git a/consolidated-00063-of-00272.safetensors b/consolidated-00063-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..04e79077717d9babd063e9520e9f38188b3192f5
--- /dev/null
+++ b/consolidated-00063-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e04875e24c29ebc03ccb2f720c41ead092b5a087d09c52b4164075163c0385
+size 2495933696
diff --git a/consolidated-00064-of-00272.safetensors b/consolidated-00064-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..79bc328de6b7bd492228450ba352c89451755d35
--- /dev/null
+++ b/consolidated-00064-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461fe3e1fb8767566b8aaaea04ee293105916dbfa808730a8d42691793372d4d
+size 2495933656
diff --git a/consolidated-00065-of-00272.safetensors b/consolidated-00065-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0782ff9a3f2c1f7ce8177d6b11efe1381528ec65
--- /dev/null
+++ b/consolidated-00065-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047d1257d08c3bb623e1132c0a294e30a050cc6b40c280fe296d465e57468740
+size 2495933648
diff --git a/consolidated-00066-of-00272.safetensors b/consolidated-00066-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..12633b59c084953f7d121b30e2255a6ec7a71c50
--- /dev/null
+++ b/consolidated-00066-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3393e4b09508bbe71a6fd88d3af8f2c3f4c47f8b250615ed788c23b80584c2
+size 2494520568
diff --git a/consolidated-00067-of-00272.safetensors b/consolidated-00067-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ee2ce3aa8013e0707bbcff61118b0fd35f7ec35d
--- /dev/null
+++ b/consolidated-00067-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5aef03f9ae155d1ea5d06e889726b1d2876b845ff105e5958ab07ec0fdc4f6f
+size 2495933800
diff --git a/consolidated-00068-of-00272.safetensors b/consolidated-00068-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2d909c51352a42430f519e1ff42322bf67ebb0c9
--- /dev/null
+++ b/consolidated-00068-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81028edf81867d056e8dfd173cacee150f5e3ebb85bdffa5ae337dab7fbec2f
+size 2495933648
diff --git a/consolidated-00069-of-00272.safetensors b/consolidated-00069-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5428806e1968f8b8e3b8f8ef01f551cf7a39321b
--- /dev/null
+++ b/consolidated-00069-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461966897dd40749cb90ce9b779b7bd675fdeb3d445de8eb838950a2ed2cc20e
+size 2495933656
diff --git a/consolidated-00070-of-00272.safetensors b/consolidated-00070-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd0cad11922ba603ff79b2835a5dedb541d4752e
--- /dev/null
+++ b/consolidated-00070-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1de23ca328cc2f6c9258a03be3353f98f39c2d510ad1832fb3f43af2f84002
+size 2495933648
diff --git a/consolidated-00071-of-00272.safetensors b/consolidated-00071-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e09b533977f621dd61c34fc97a938cbd9714ee3a
--- /dev/null
+++ b/consolidated-00071-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87fef4bb78ad74c8e37de63ef9eec32c1fafe3b88f8331ee1bccd1efb58989de
+size 2494520776
diff --git a/consolidated-00072-of-00272.safetensors b/consolidated-00072-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..22725fe00117785cb23c0dbed6b4ef8c843842d9
--- /dev/null
+++ b/consolidated-00072-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacbd96bbacdf769a359347a5e409d7873120da4780addbb7d7d85c43fe1b9a7
+size 2495933744
diff --git a/consolidated-00073-of-00272.safetensors b/consolidated-00073-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4e745ac2f951d973bdebd33d9bc8955a3b6085ab
--- /dev/null
+++ b/consolidated-00073-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd461d134572c4a3917eba45af32c8abbe3ecc38e24231a37b09c4d5b6b49eba
+size 2495933648
diff --git a/consolidated-00074-of-00272.safetensors b/consolidated-00074-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..18bb3c8a7bc3fccc98dac995a12b7f1368a59596
--- /dev/null
+++ b/consolidated-00074-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7934d4ded8eb454b8e807f0b8a7dc65b646b6b7a1efeb5ad225565175bf7e69
+size 2495933656
diff --git a/consolidated-00075-of-00272.safetensors b/consolidated-00075-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..11b61dcb202b4fe99b8ce0a77cfa5df584ea0e0f
--- /dev/null
+++ b/consolidated-00075-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c0d3a3df6128fe56d460fdb8fe252f699f4bd395a7756003b410fbfd2950e0
+size 2494520448
diff --git a/consolidated-00076-of-00272.safetensors b/consolidated-00076-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..37de64dac3ebe94b4b8987be7975bdcb5b6f2069
--- /dev/null
+++ b/consolidated-00076-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34586647d64b356d480269455ea9d1a32dbe46f436ff0b7d980619963489860
+size 2495933800
diff --git a/consolidated-00077-of-00272.safetensors b/consolidated-00077-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8fb3315890f599eb3a4edc80d5593f0108ae7934
--- /dev/null
+++ b/consolidated-00077-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f4015c48062ca7b43b55e4e789c0be295c12ca788342a263de68665122c23b
+size 2495933680
diff --git a/consolidated-00078-of-00272.safetensors b/consolidated-00078-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e47de9f7b4f05cbaddce4e49877b620a05e23eb7
--- /dev/null
+++ b/consolidated-00078-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce9ccedb1d90e454a749f80bf03f8c9d9ae7d282b73d7dc67e882342c4a5e6c
+size 2495933648
diff --git a/consolidated-00079-of-00272.safetensors b/consolidated-00079-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..206200e422a5318f5673092160cc5267ee385245
--- /dev/null
+++ b/consolidated-00079-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ca70d68156792540f50aebaccf6d4a3f4ddc317603d242d7937a97a6bf709a
+size 2495933656
diff --git a/consolidated-00080-of-00272.safetensors b/consolidated-00080-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..eb6157a5a81bd49ae6b374bd87202cc0b99b2c45
--- /dev/null
+++ b/consolidated-00080-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8af1edeacf9eb47161e90f4d91e4c6d0a6da818adb744849c287fe52782e61
+size 2494520616
diff --git a/consolidated-00081-of-00272.safetensors b/consolidated-00081-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d60b865f74f001b46c00a7e5491119df3b505008
--- /dev/null
+++ b/consolidated-00081-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6414646dc78e980aef520a8fd9cd8ea6d04c95b6b2fcf8248847fc1dc6c88d37
+size 2495933784
diff --git a/consolidated-00082-of-00272.safetensors b/consolidated-00082-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0d71e76e77dbdebc93b35c3d044b23c5fc234985
--- /dev/null
+++ b/consolidated-00082-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e049147decaf443719c9e7584b15cdb656fd9b09955f5e43babac364787f7a
+size 2495933648
diff --git a/consolidated-00083-of-00272.safetensors b/consolidated-00083-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..20eed5585a389fa6422e47cc2d2483ce3f581d9d
--- /dev/null
+++ b/consolidated-00083-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6d319a503fc90f8d808e94b953c9204b8964c5589f1e5b7d5b35a659477fc7
+size 2495933648
diff --git a/consolidated-00084-of-00272.safetensors b/consolidated-00084-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5dc61f31d1517a2700f9ca429391eaaa0b61a16
--- /dev/null
+++ b/consolidated-00084-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5b2f57d3b87c58f8085771780e0373fd2d78fccfaf826c88ca56da5e21a7a4
+size 2495933656
diff --git a/consolidated-00085-of-00272.safetensors b/consolidated-00085-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6c29e65eedb4857066b6aae283132ba8d5e070bc
--- /dev/null
+++ b/consolidated-00085-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b651ad597a5fddaac68b81f6e7c4ec08bfc671f23cb70477d56555aaf6a22a
+size 2494520840
diff --git a/consolidated-00086-of-00272.safetensors b/consolidated-00086-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6ab009d4f20345a401e44963e9d6b31e5cca8380
--- /dev/null
+++ b/consolidated-00086-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2b318fb0f851b67b45218fa8261e6236237f249e9a0ec08d61870b84587dca
+size 2495933728
diff --git a/consolidated-00087-of-00272.safetensors b/consolidated-00087-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ab27dca70e3aa0f13b263b7a5a67234ae5e306fc
--- /dev/null
+++ b/consolidated-00087-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adccfd9bf3186fd9c573cff701e151bb30ec64830c8c10d905752208d06357fb
+size 2495933648
diff --git a/consolidated-00088-of-00272.safetensors b/consolidated-00088-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..93c65968287aa406aa5b4a2b81ba8818d7a840f7
--- /dev/null
+++ b/consolidated-00088-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2eea5eccac9496b1be57e6d2d55501e520a53b37bffba6c2412593537633456
+size 2495933656
diff --git a/consolidated-00089-of-00272.safetensors b/consolidated-00089-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3cdf041dbf4a6a7f43849469bb9b5d89e808966f
--- /dev/null
+++ b/consolidated-00089-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5de6ad3bf7c86e2e60a757d2f970835906249b3c01bfc68a6cd67e0f4893012
+size 2494520472
diff --git a/consolidated-00090-of-00272.safetensors b/consolidated-00090-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5267b4d1d7b1ec622f4fe409a478e66d57018fc5
--- /dev/null
+++ b/consolidated-00090-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a067ea07a02372140c2636b2a61a6969f3783b2b51252b70226d0c75e8ca30cd
+size 2495933824
diff --git a/consolidated-00091-of-00272.safetensors b/consolidated-00091-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c38489f2d82a821d96a0987e5c1b6af1c0a1e5b7
--- /dev/null
+++ b/consolidated-00091-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0112cbffa6aa717421a8fb8da6c3efabbe206e4ee37fdc726b8d019c7ed451
+size 2495933664
diff --git a/consolidated-00092-of-00272.safetensors b/consolidated-00092-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..90c9c89a47a954775f45a2672312bdebd25c3749
--- /dev/null
+++ b/consolidated-00092-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306d9a2c6b5e5ccc48e163d83b5cebb326e375270918a654263ceac1def540e2
+size 2495933648
diff --git a/consolidated-00093-of-00272.safetensors b/consolidated-00093-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e64fa482d6aef3c457977ff91fdc470bee34709
--- /dev/null
+++ b/consolidated-00093-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74cedfe998db8a38e3b0f0829f6af9e9956e8a2bce08f92c706ac85620a1e3
+size 2495933656
diff --git a/consolidated-00094-of-00272.safetensors b/consolidated-00094-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6550a9465a5e13b097a2ed1831ca1b1b63491d1f
--- /dev/null
+++ b/consolidated-00094-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d13777008707ff842f6f9d89ea27ca1cbb3c8e8c5048bd04f32667122438e4e
+size 2494520568
diff --git a/consolidated-00095-of-00272.safetensors b/consolidated-00095-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6515aa264c9fd943e227ab2eaffff05bedd9381e
--- /dev/null
+++ b/consolidated-00095-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8a2682a8d5f886120c951c730fcbc25c65f2ee78f1dab395c3acfcde2b3352
+size 2495933600
diff --git a/consolidated-00096-of-00272.safetensors b/consolidated-00096-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9f10e7eb1a06426b3820d6db8b50ea0128d5d6e8
--- /dev/null
+++ b/consolidated-00096-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2989f21b34fcd221e31e8d62428a1244d563ea42f63fa65b1e0936be74f1b335
+size 2495933488
diff --git a/consolidated-00097-of-00272.safetensors b/consolidated-00097-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9713e32694e44f60663a4b267520b85681eccba4
--- /dev/null
+++ b/consolidated-00097-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5201ae14be23ac5a3c5e35b0d8644d0fd20d39a333c0c719f6053dd10a16436a
+size 2495933480
diff --git a/consolidated-00098-of-00272.safetensors b/consolidated-00098-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e59dc68beded7a0a3abe5e2832597705ad3340f4
--- /dev/null
+++ b/consolidated-00098-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3416d626db667c1f57782e0dd361f502e1a77f22c68153ec4b29d74b0659b1a3
+size 2495933488
diff --git a/consolidated-00099-of-00272.safetensors b/consolidated-00099-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..077f1ab40ac2ac4fe75ab8821aa6741ed11a7f4b
--- /dev/null
+++ b/consolidated-00099-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff287a0629a87d5e1ca876056976d4af18fe4e0d42e3f985ecb4f55936ac070
+size 2494520888
diff --git a/consolidated-00100-of-00272.safetensors b/consolidated-00100-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7401893d9b773d4d1b0cf783c2604b99d9fc7b45
--- /dev/null
+++ b/consolidated-00100-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55c4d6ea30e365dcd74378c3c8658870bed7c24ad045536f6f824547aa87208
+size 2495933704
diff --git a/consolidated-00101-of-00272.safetensors b/consolidated-00101-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e07f3fff3a73ff56706238937a2a80adaba33543
--- /dev/null
+++ b/consolidated-00101-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb449b923a287c4a16240d0b9def8d7e8cc556d5dd1e5a07db4d1ce89155073
+size 2495933656
diff --git a/consolidated-00102-of-00272.safetensors b/consolidated-00102-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6679f7ba28ff6293249d763519b51cf13181fe86
--- /dev/null
+++ b/consolidated-00102-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020801705767fc131f0408ef454a6eed0440db047ffec01cb077f48e94254db3
+size 2495933648
diff --git a/consolidated-00103-of-00272.safetensors b/consolidated-00103-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ddb118f08f40cd4b9c1d0b23206a83d69e210aa8
--- /dev/null
+++ b/consolidated-00103-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cceb23ff462f4d7a5275a76bcd86e1c1b1517c8d66fe418b147156d98566283
+size 2494520528
diff --git a/consolidated-00104-of-00272.safetensors b/consolidated-00104-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..952abc99a329d917b299b8eed6affdacedc9a091
--- /dev/null
+++ b/consolidated-00104-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8927245e94f6bdf54377ecdaeb924b67a8db84dc7452f7d68f2d11ef98da70d
+size 2495933816
diff --git a/consolidated-00105-of-00272.safetensors b/consolidated-00105-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ffed8ede1914acb26a869cbf84008f9a1f1ba64b
--- /dev/null
+++ b/consolidated-00105-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3cd7b10a3e0769f65125623e2f700d3347d01fb69ca60898aac0383abcef594
+size 2495933648
diff --git a/consolidated-00106-of-00272.safetensors b/consolidated-00106-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..73f1599ca5225cbc064f04dae08c0c153eb582e1
--- /dev/null
+++ b/consolidated-00106-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1065e8d83e6a483894e07957610de86e8a2f0ef01f47e8125c3b837ed95be34
+size 2495933656
diff --git a/consolidated-00107-of-00272.safetensors b/consolidated-00107-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4ac568eaac301b69f0b7f85dd15cd1c76df7cd3f
--- /dev/null
+++ b/consolidated-00107-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd48d9e63ea5e79986f87930059aa502602a1d57409267dac5bd971e2a97dda7
+size 2495933648
diff --git a/consolidated-00108-of-00272.safetensors b/consolidated-00108-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..449147fad85a6bd9804f039f08974dee8fce4baf
--- /dev/null
+++ b/consolidated-00108-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b1f4a1fc53cf3fb1dbef1964d7c2b575cc7008360017088f98c821f776ccb8
+size 2494520720
diff --git a/consolidated-00109-of-00272.safetensors b/consolidated-00109-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5903d72cbd1ba7db4157c8c002c55745e861c0f9
--- /dev/null
+++ b/consolidated-00109-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d656c9c2eb501811ab7f5768cd52d62176c154d5d9c1068f10b6ef9e6140f07d
+size 2495933752
diff --git a/consolidated-00110-of-00272.safetensors b/consolidated-00110-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..519232414941b8ecc33ceb27b2140b1a923af130
--- /dev/null
+++ b/consolidated-00110-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec626abde80ec60c963e846594ef4d85e5dbf1c585514fe062d44f6e0f15d8f
+size 2495933656
diff --git a/consolidated-00111-of-00272.safetensors b/consolidated-00111-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8552aff9d6011a48be9660d0193d8332611182d6
--- /dev/null
+++ b/consolidated-00111-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0724385336431eee6ae0258a72f0e5171fe46ccb83ae7a6c6413b8ab5965f1aa
+size 2495933648
diff --git a/consolidated-00112-of-00272.safetensors b/consolidated-00112-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f2ebae77f569913a8a89faf9fc37fa2b78f330be
--- /dev/null
+++ b/consolidated-00112-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4b8bd37863b855d14905f138e3f9bf54587162029e6f773e1f6ad47d0dc385
+size 2464096800
diff --git a/consolidated-00113-of-00272.safetensors b/consolidated-00113-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d40f5304eb1080ce66c47412d11bfd8dafa3fe34
--- /dev/null
+++ b/consolidated-00113-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b01bb46952af21c52aaf4fdb47279d981c97276cbca97f6325098c76448eb1d
+size 2496993872
diff --git a/consolidated-00114-of-00272.safetensors b/consolidated-00114-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bb24884ce35d5e5e8174f6bd0d9c5a9b9ab528bc
--- /dev/null
+++ b/consolidated-00114-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fff21e0ad5bea86486e04ae9f43cf0da2bffe42bee6783207524bc251df9ce
+size 2495933696
diff --git a/consolidated-00115-of-00272.safetensors b/consolidated-00115-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1df573778840ad6ad40e0b7868cf94e59514629d
--- /dev/null
+++ b/consolidated-00115-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00fa0d9ce88e02f5aecd7061fa8b3d37ce8485d775ccb4714b8b88081a81734
+size 2495933656
diff --git a/consolidated-00116-of-00272.safetensors b/consolidated-00116-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cb3b34e53f1564f493bf1e143a6cc18b15cc9b86
--- /dev/null
+++ b/consolidated-00116-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8856957b7a2de3c5b2c29d6f7e9a3be42fec5a87717794e291bbdd8a11253ad7
+size 2495933648
diff --git a/consolidated-00117-of-00272.safetensors b/consolidated-00117-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8e3b5eb98801cbf7fd8bd878983c9c04a6ecd70a
--- /dev/null
+++ b/consolidated-00117-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6966763b36d63846402a47afe752ae420e875c886d1361c5904cf74ffd303b
+size 2494520568
diff --git a/consolidated-00118-of-00272.safetensors b/consolidated-00118-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2b4c85bf35d3adc2ab2012f3f21ff00689dc892c
--- /dev/null
+++ b/consolidated-00118-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bad41efbd037d9c3e079f1d8d8e3c19efdc3cb40a8f9ccd8f4218ee5e609dc5
+size 2495933800
diff --git a/consolidated-00119-of-00272.safetensors b/consolidated-00119-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c64a7729607dbe55f4a18e071c90f94906fe1352
--- /dev/null
+++ b/consolidated-00119-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510dd8cc1fafd3ef4a1fcb6f03733f80db65d14f98e2fdb639a1ecf990d440d0
+size 2495933648
diff --git a/consolidated-00120-of-00272.safetensors b/consolidated-00120-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0ba590c4101ad33c4c9ce4390018226a21d5c804
--- /dev/null
+++ b/consolidated-00120-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a90449a2123f88481efe87e05082ef7d20bcdd188e7d64c2bc8c09ff853869
+size 2495933656
diff --git a/consolidated-00121-of-00272.safetensors b/consolidated-00121-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c94d2c4ad7a95e019dea50149a224e496c4038c8
--- /dev/null
+++ b/consolidated-00121-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26370d4171382ec70ad26332a3337edd4ab79d1de618b930e6f16efe24e3017f
+size 2495933648
diff --git a/consolidated-00122-of-00272.safetensors b/consolidated-00122-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7074d4edfbbe38b136e0ba09295f115eff40b9e7
--- /dev/null
+++ b/consolidated-00122-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452ebb585ad26312be1d9bdb5d9b27f897a3f07bed42fa6c883264b86f66da3a
+size 2494520776
diff --git a/consolidated-00123-of-00272.safetensors b/consolidated-00123-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..adc1b521c9cbce71d00312bc48c7fe24628368b6
--- /dev/null
+++ b/consolidated-00123-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfe4704e36bc04cb996b4a8f55a1effd72be9de559f65b808f47fa220975596
+size 2495933744
diff --git a/consolidated-00124-of-00272.safetensors b/consolidated-00124-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..02de0427f518580955c0b5ee9c892412277e342a
--- /dev/null
+++ b/consolidated-00124-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34052a87af59577ee63dfd6e8cfef6dedee070b05505b2298d6889c4764978e5
+size 2495933648
diff --git a/consolidated-00125-of-00272.safetensors b/consolidated-00125-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e527d3ef4271a65dfa50a367dadf7c2b9b248a2
--- /dev/null
+++ b/consolidated-00125-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa5c53a9bdbf190b791dbf1865f971ed27f1ccdc738a52d59b0ee64eee3eb3d
+size 2495933656
diff --git a/consolidated-00126-of-00272.safetensors b/consolidated-00126-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8e27d2e5951f0292cd72d90104fc4308bb187941
--- /dev/null
+++ b/consolidated-00126-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84eb66b606cb309c904b9506383c7246e2fb23b6cc7b4e3065ac274179fbaa8
+size 2494520448
diff --git a/consolidated-00127-of-00272.safetensors b/consolidated-00127-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6b431e28bee4ebecd78f7d2c503c6aaebd61774d
--- /dev/null
+++ b/consolidated-00127-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018eb5720219103067381db850e8cbc2c160b76e2f37ae3e364df7a769797019
+size 2495933800
diff --git a/consolidated-00128-of-00272.safetensors b/consolidated-00128-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dd97ad29e2247afd33d932dd61a07d8b9b54357a
--- /dev/null
+++ b/consolidated-00128-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c76cb4ecffc765fd14d341ad9887e25725d1eff8b893deeb5ff3a74608722c7
+size 2495933680
diff --git a/consolidated-00129-of-00272.safetensors b/consolidated-00129-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b3b8b375e92f9b2e949ac454fe4813aaffc8a74e
--- /dev/null
+++ b/consolidated-00129-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3229c45531e7d4a79f6dcbae30ba7cf532d1ea6b31c3727a8565a7546d179f0
+size 2495933648
diff --git a/consolidated-00130-of-00272.safetensors b/consolidated-00130-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d1851217d20faa7deb664f8972656fc91a998b38
--- /dev/null
+++ b/consolidated-00130-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5930917a254ae2eb003d813be5443b7182495c25779ae2d2f06b192c22ab3d
+size 2495933656
diff --git a/consolidated-00131-of-00272.safetensors b/consolidated-00131-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..37b0b6049da511a98849de212a2b5e3715ca8324
--- /dev/null
+++ b/consolidated-00131-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2efffae3973c7bdee4158da1792c1d3e3f093cc184e433205bf6b78ffd52a9
+size 2494520616
diff --git a/consolidated-00132-of-00272.safetensors b/consolidated-00132-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1149d0d031c7bf52248d3a0d7ff3ece32997bc42
--- /dev/null
+++ b/consolidated-00132-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74624b1f308f381d04bb6db858a5194d53b9af099f9a218a50c7279472f0217
+size 2495933784
diff --git a/consolidated-00133-of-00272.safetensors b/consolidated-00133-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..19f1f9ae2b2bbf5d7a06fbd463f384fd58df2a81
--- /dev/null
+++ b/consolidated-00133-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bccbd24b6f9b6e884bbe0e6c0f6c6c683ddea3f8e7e3b0593f236776d2de22
+size 2495933648
diff --git a/consolidated-00134-of-00272.safetensors b/consolidated-00134-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e4c7c6fa9be41df6955225b0091966615ccc9ca
--- /dev/null
+++ b/consolidated-00134-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b62bd6bc5cb669cfec26a63b36f094a59723beaf47874d1e507a1cce2b9547
+size 2495933648
diff --git a/consolidated-00135-of-00272.safetensors b/consolidated-00135-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c1338084eb6f2bd52234f62d2959319fd40dc58
--- /dev/null
+++ b/consolidated-00135-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c00d34b12c4bad1ea986e11028a30fdcf6430101de13a7565d815376b1eca05
+size 2495933656
diff --git a/consolidated-00136-of-00272.safetensors b/consolidated-00136-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40f03493fdedad5dd5aaffbad8c8e262fb9ce240
--- /dev/null
+++ b/consolidated-00136-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a48d25133b50b6f1ef2c0ce94c7ac6c043f9ecc22b0729219ea042d9b1ef0f
+size 2494520840
diff --git a/consolidated-00137-of-00272.safetensors b/consolidated-00137-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f7bb87dc01dac59e3baf1ac2e13810fde809be2c
--- /dev/null
+++ b/consolidated-00137-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6195c170609bf67b2d8817ab0a5d208e834bde96550beb349afc656b801afa
+size 2495933728
diff --git a/consolidated-00138-of-00272.safetensors b/consolidated-00138-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..276fab1c09116cd2b2ff8d42ec6485d33bd07c01
--- /dev/null
+++ b/consolidated-00138-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7d1560a75e7bf3280f1d61191cfc510608c3ef4e535e4e29c8ccd1d9335f6e
+size 2495933648
diff --git a/consolidated-00139-of-00272.safetensors b/consolidated-00139-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d8c9337822b7a168fce94764c3cdc9028901cd6d
--- /dev/null
+++ b/consolidated-00139-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004e00b57579a1d4bef04630c9e556e429fd4fadc68e9daffed3a00532fd66f8
+size 2495933656
diff --git a/consolidated-00140-of-00272.safetensors b/consolidated-00140-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f1cd2eca39dd80f15579849164684675f477a9b7
--- /dev/null
+++ b/consolidated-00140-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9192884e50c37928743deae79556da49f0b2bd9c5ec6ebb7c2afc7855f06c1
+size 2494520472
diff --git a/consolidated-00141-of-00272.safetensors b/consolidated-00141-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d676145875edf23388c4b0cc003de62e6f5169a3
--- /dev/null
+++ b/consolidated-00141-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bd3c7fbbabde896e84760d60ac403b6e2c83de09dbb9579b5cc32857fd0a25
+size 2495933824
diff --git a/consolidated-00142-of-00272.safetensors b/consolidated-00142-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e15454d02ad792c9ac690045e9da4076ba4f1524
--- /dev/null
+++ b/consolidated-00142-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0d5622045f3ee88f00a2744fadb9914d0564475ad44d69bed401ab8ff95dd9
+size 2495933664
diff --git a/consolidated-00143-of-00272.safetensors b/consolidated-00143-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d419a3391e025e3963fbffc8ba5441854a199464
--- /dev/null
+++ b/consolidated-00143-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef7c6a328471b59a13136ed9446f52944371b3635531d4c55fb5fd3748a0df7
+size 2495933648
diff --git a/consolidated-00144-of-00272.safetensors b/consolidated-00144-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7a5da047affdd5942e24dbfc401d72873de3d199
--- /dev/null
+++ b/consolidated-00144-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de9bc5b13cce58d43b305c1e27dbf5efaa4b376772baa6c4896694e2092a718
+size 2495933656
diff --git a/consolidated-00145-of-00272.safetensors b/consolidated-00145-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..88c0c3974e7bbdd15556a7f6dfe4a3c06f27099e
--- /dev/null
+++ b/consolidated-00145-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff9cdec194c282cb52c7129dc186ed512b161c077fc209910d7b3b0f2427002
+size 2494520568
diff --git a/consolidated-00146-of-00272.safetensors b/consolidated-00146-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e1ee19e3af91b913281582c91433c84badc8f5d0
--- /dev/null
+++ b/consolidated-00146-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd794aab1020ccf12915be08b0b6a8049a7b550934643de2512c55670795689
+size 2495933600
diff --git a/consolidated-00147-of-00272.safetensors b/consolidated-00147-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1df0cb1bd2e289a1d54e0e452e0930eee49befa9
--- /dev/null
+++ b/consolidated-00147-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76291c967dc9dd925b790de84579eac23c8f9074694c868945d9b27ecf010858
+size 2495933488
diff --git a/consolidated-00148-of-00272.safetensors b/consolidated-00148-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a05f828fc5bf98601042e25d0418325058792f45
--- /dev/null
+++ b/consolidated-00148-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdf88f8bff28352b243960b9e1f3aa97d5396799079be05ce9960961373d694
+size 2495933480
diff --git a/consolidated-00149-of-00272.safetensors b/consolidated-00149-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..283929f66001f9e6f7b09f48dd23ecf3f623c31e
--- /dev/null
+++ b/consolidated-00149-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0970a32c18e4e8be22012055caea817fd776429aed896cf926f7f40798c7fc
+size 2495933488
diff --git a/consolidated-00150-of-00272.safetensors b/consolidated-00150-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd98d5e7b30193f0afbe8c8de66fc35076fe4598
--- /dev/null
+++ b/consolidated-00150-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ec1e38ebbf8093e708d310a9cc3d77556667791474a2b7e1e1c5fcc843fe89
+size 2494520888
diff --git a/consolidated-00151-of-00272.safetensors b/consolidated-00151-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e342af0456153e4e3597a87adcfa73078d45768b
--- /dev/null
+++ b/consolidated-00151-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ca46642d94be5c9f5f5a92ca7f8307775fde04636a86694ab3d14e7085e05d
+size 2495933704
diff --git a/consolidated-00152-of-00272.safetensors b/consolidated-00152-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..faef47f7e6690fcdc833323e872c3ad3bd39d044
--- /dev/null
+++ b/consolidated-00152-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68fdb80bb5cbb7d4d2b3f8cb72b21ca06b257da7090484fbda7eb9d4014d2d17
+size 2495933656
diff --git a/consolidated-00153-of-00272.safetensors b/consolidated-00153-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4c7fb29707a93d1188c27ea15e58267fc7d61c18
--- /dev/null
+++ b/consolidated-00153-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb05f4f9a6371f2e0e083cd1508ccfab89a8adb3ba0294173d715a436ea1214
+size 2495933648
diff --git a/consolidated-00154-of-00272.safetensors b/consolidated-00154-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..16748a945185c4fc068c15c2ea9d0b7942244858
--- /dev/null
+++ b/consolidated-00154-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca1a7d138960256facf0a8132eb10f7248311fbd7809f8dad95746dc8d5ad4b
+size 2494520528
diff --git a/consolidated-00155-of-00272.safetensors b/consolidated-00155-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2317ef341492b3c571aebf387bbc00528db9fa85
--- /dev/null
+++ b/consolidated-00155-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff510aab7454c0f6f2cf794962537aa2ba6355514a62c86befc394181fb669a
+size 2495933816
diff --git a/consolidated-00156-of-00272.safetensors b/consolidated-00156-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..52d9f2b6707a0b7a35fdbb31cec8a5089a0a949f
--- /dev/null
+++ b/consolidated-00156-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2262b5a269eff1d4bb44f06c704ad90dfbd19a18cbf21036b14e387c9a08a29d
+size 2495933648
diff --git a/consolidated-00157-of-00272.safetensors b/consolidated-00157-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e79cbe358524636444bb3d2afd76e505728043fa
--- /dev/null
+++ b/consolidated-00157-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed275829a714752ee53a25df33c28a330e59e2cf6f9adaf0845523c27b9762b8
+size 2495933656
diff --git a/consolidated-00158-of-00272.safetensors b/consolidated-00158-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d454532eb07edae25694176a63c6b640a19fffbf
--- /dev/null
+++ b/consolidated-00158-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72486185ed7991dc30f6f6f6ff7d7f34a5ade7509063de352df3400a23b1e20
+size 2495933648
diff --git a/consolidated-00159-of-00272.safetensors b/consolidated-00159-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..45280c12f7f337d645f34fb624b30314a6f2f6f2
--- /dev/null
+++ b/consolidated-00159-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525f98c1903c40450b265da7e806521ee37b03f48a057370891474a5c5f63485
+size 2494520720
diff --git a/consolidated-00160-of-00272.safetensors b/consolidated-00160-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..752a317864b5e85948106fe6a7428a0be428e755
--- /dev/null
+++ b/consolidated-00160-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4321eed5678de80326d942771e49a162d07b09ce70b5ee642519f71d86e2e59
+size 2495933752
diff --git a/consolidated-00161-of-00272.safetensors b/consolidated-00161-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f8c0c378b6e2ea0c48fb31659c2e7c27d47c384f
--- /dev/null
+++ b/consolidated-00161-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece31164861e1dc3eee5d037f792710c1dfd5681b2200f701746695aac555f1e
+size 2495933656
diff --git a/consolidated-00162-of-00272.safetensors b/consolidated-00162-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b674558a394521bd2f53b73670babcf79eb01f26
--- /dev/null
+++ b/consolidated-00162-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b0559598a50d4d6a6f2aba6b1996bdee21a6053503b67f073285db9debbd5d
+size 2495933648
diff --git a/consolidated-00163-of-00272.safetensors b/consolidated-00163-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c49b7f8f77c41520148ed0687799ac09ab40da4
--- /dev/null
+++ b/consolidated-00163-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530679e940c0b645cc73927ee1beabc1a5ee94d198310ce5a4c39dd4fe15b513
+size 2464096800
diff --git a/consolidated-00164-of-00272.safetensors b/consolidated-00164-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..adfd344cd8644fc758504d356bb9327fa4cbc26f
--- /dev/null
+++ b/consolidated-00164-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dac2515e740efd137eda39aaea492ac363ee508fa9b4e1d4d8760d68d8ca558
+size 2496993872
diff --git a/consolidated-00165-of-00272.safetensors b/consolidated-00165-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2b993bc64aa19bfe5d86b71af988e813a535b01a
--- /dev/null
+++ b/consolidated-00165-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db3ad918ea4b3b0c986f5841a9c8ef07771db495144a1bfc0def1c0d7e358d8
+size 2495933696
diff --git a/consolidated-00166-of-00272.safetensors b/consolidated-00166-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e99033a16cbd9187e6d482f3096fb7598f28c779
--- /dev/null
+++ b/consolidated-00166-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17734e9a29f73d94d016dd9145856bf170e2aa38caff42468841d82bd050a14
+size 2495933656
diff --git a/consolidated-00167-of-00272.safetensors b/consolidated-00167-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fecad8e0b4d0eecf7a5f82e1570942f64461ca77
--- /dev/null
+++ b/consolidated-00167-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69edb8bdaa2067ddc8737a2e760207a4976d6755f283a8f1050072022c1dec18
+size 2495933648
diff --git a/consolidated-00168-of-00272.safetensors b/consolidated-00168-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..724859b4097298670e687628f34d2e1bbbf96c16
--- /dev/null
+++ b/consolidated-00168-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414da664df993b367a2c44e970ce55cee0421b15a00f7cce77c41898c6ecf659
+size 2494520568
diff --git a/consolidated-00169-of-00272.safetensors b/consolidated-00169-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ddb7bc43d1701e822509c26dd3b6047db25aef77
--- /dev/null
+++ b/consolidated-00169-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7425e4c606f3e0f0377699db1931f186599e7f02114d265a99bf8a77f35eed09
+size 2495933800
diff --git a/consolidated-00170-of-00272.safetensors b/consolidated-00170-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d71412b5a26fa3f9f58d3d782c8df5a4bce855df
--- /dev/null
+++ b/consolidated-00170-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d18fdf9e9817a8e61cca3453cc72730de27327d9018dafb416f6dab2be16d614
+size 2495933648
diff --git a/consolidated-00171-of-00272.safetensors b/consolidated-00171-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..700d765253c433d5dca4c822e3d7429685713d83
--- /dev/null
+++ b/consolidated-00171-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9762d90c4401e5557b49991d8497d21910c9c6859f14caec389903712fa534e
+size 2495933656
diff --git a/consolidated-00172-of-00272.safetensors b/consolidated-00172-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..985b893ff4f3239f134f4d8a9fca274c75a9eb7f
--- /dev/null
+++ b/consolidated-00172-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4c25293f7c42ca65a37450adbe6c4e4c3cf589c68184258152a4421b9d65ae
+size 2495933648
diff --git a/consolidated-00173-of-00272.safetensors b/consolidated-00173-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0091bbb41e71a0dfe40afe065190afa706cb23f4
--- /dev/null
+++ b/consolidated-00173-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca8b6b8065720cd6949a6c695a9dd8a2a1f48ea74c1ac33bdb381418570460a
+size 2494520776
diff --git a/consolidated-00174-of-00272.safetensors b/consolidated-00174-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f2308cf69e3fedce55fa418bd427164cab1f477b
--- /dev/null
+++ b/consolidated-00174-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb985964bed782b045c45bf12182ee4a95ab491ea51381824c92a540a80db1be
+size 2495933744
diff --git a/consolidated-00175-of-00272.safetensors b/consolidated-00175-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..92fc7675e23b21227a6ea47fac6ffe44375dfe5f
--- /dev/null
+++ b/consolidated-00175-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a21390fa9d18dc184f22d540d06800c28e24035a064cab4ccca64e9a4059c4
+size 2495933648
diff --git a/consolidated-00176-of-00272.safetensors b/consolidated-00176-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7965a129cbf3d859729a7c0a2b7ebb1065dd149
--- /dev/null
+++ b/consolidated-00176-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f5f6ba4716e1e50a9e8c03c6583442534d97cacfc6a57bb0b085ac083166bf
+size 2495933656
diff --git a/consolidated-00177-of-00272.safetensors b/consolidated-00177-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d7d644f62026d2f3f3972edea9a1000de382d749
--- /dev/null
+++ b/consolidated-00177-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bceb085dc500631b750b9b1ef09714b1e31f1279b8b029a3d26a2a20c56da987
+size 2494520448
diff --git a/consolidated-00178-of-00272.safetensors b/consolidated-00178-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..541fc8cec2f3bf682ced39ca3b14ebe4442fc02f
--- /dev/null
+++ b/consolidated-00178-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758f79544fa63238dd64eddb3c724244ee8a1eefb187acda8e3aacaad325e80e
+size 2495933800
diff --git a/consolidated-00179-of-00272.safetensors b/consolidated-00179-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..31ca03b9b0ad5c67df6353c0c9222b0ccd839384
--- /dev/null
+++ b/consolidated-00179-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81402801dd55cd6a50e9eb2977eeabce6d90abdb21db2576e9e52ccd4069314c
+size 2495933680
diff --git a/consolidated-00180-of-00272.safetensors b/consolidated-00180-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ba2bf84746555d64201fc03ee4fc36f4aa186892
--- /dev/null
+++ b/consolidated-00180-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1632d2de5c75fd38215ba1803e25aa04821d518732968eae6e497b3ade3241
+size 2495933648
diff --git a/consolidated-00181-of-00272.safetensors b/consolidated-00181-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..61605bbf0a8745f461a2d476a17888628d8f6c1e
--- /dev/null
+++ b/consolidated-00181-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e08bc8a423be589c6fda571904bebac332247b8657720391ccb59156b016340
+size 2495933656
diff --git a/consolidated-00182-of-00272.safetensors b/consolidated-00182-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a29fee3beb06b385bc9e9b449601e09b389a306d
--- /dev/null
+++ b/consolidated-00182-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca523939f74a67097d76e3de02e504c378b90dd267ff47d692f934c1dbe3bea
+size 2494520616
diff --git a/consolidated-00183-of-00272.safetensors b/consolidated-00183-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..01587a7413ae0effed88acabf2d6db191b510794
--- /dev/null
+++ b/consolidated-00183-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45832fb9d6945e0715dc80a8a432ec84fac0600a9f7fea3cf7edda0819bbd07
+size 2495933784
diff --git a/consolidated-00184-of-00272.safetensors b/consolidated-00184-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a957e7bbfcef6afab2a435890743326868c34471
--- /dev/null
+++ b/consolidated-00184-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d4e5b3eebaa65ead9643154089a74fe817e8d5aa6b859bd5be10894dedf375
+size 2495933648
diff --git a/consolidated-00185-of-00272.safetensors b/consolidated-00185-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..636ea804ceea812fceb5ef15a2b016c3df6d1984
--- /dev/null
+++ b/consolidated-00185-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e733a88980ce1732d097343b6d40df244c8e5b2054fd3c652d83a564f73a7f9f
+size 2495933648
diff --git a/consolidated-00186-of-00272.safetensors b/consolidated-00186-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e027f07cc9b5b25d4bf7668fe2b2c527bbc5aff
--- /dev/null
+++ b/consolidated-00186-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b283f6f03bbd99d4e9767a33ff3814fb5ed74d3c45a495386879161e09bdf5
+size 2495933656
diff --git a/consolidated-00187-of-00272.safetensors b/consolidated-00187-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ab6ddf5d20bfe7608b2738e2d9ca91f5fdbad941
--- /dev/null
+++ b/consolidated-00187-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc552b889ebf641f07acdcedb0b3d0df088c96dbcc47e9d8d819316356ec1d8
+size 2494520840
diff --git a/consolidated-00188-of-00272.safetensors b/consolidated-00188-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..83c2c018c3416b9b9041a181abb7e028e54e1e5a
--- /dev/null
+++ b/consolidated-00188-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb21e6fb143e448b56127bcfaf03b8de1976d8c66acaa9953f509098f1d8d029
+size 2495933728
diff --git a/consolidated-00189-of-00272.safetensors b/consolidated-00189-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fb3aa19bbc6c1789546d9616474a83413f4563dd
--- /dev/null
+++ b/consolidated-00189-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dee66ba3d7711502c1b7579ea3ccb450bc2701ec63601e44e77a069fdfa4100
+size 2495933648
diff --git a/consolidated-00190-of-00272.safetensors b/consolidated-00190-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..41ebf075bc930d34ccb02a74ebbc9004d91dcf79
--- /dev/null
+++ b/consolidated-00190-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762195690c2e422d3edf7bf8e789cda294e99367d47b7d36d7bb801815a54463
+size 2495933656
diff --git a/consolidated-00191-of-00272.safetensors b/consolidated-00191-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b4bbd3f1ade20b7795fb929991246b5f9677c767
--- /dev/null
+++ b/consolidated-00191-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818903a6cf8140081fa252a4f8fed23399b4f07ba8881a737ebdd2aa8dcf4bbd
+size 2494520472
diff --git a/consolidated-00192-of-00272.safetensors b/consolidated-00192-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4c2c8539ee60206b8daa659e3afbc8faf74cb439
--- /dev/null
+++ b/consolidated-00192-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ee203614d8f95c40b338059ec4c502eeea329747d7747ffa30c9b3ed40af60
+size 2495933824
diff --git a/consolidated-00193-of-00272.safetensors b/consolidated-00193-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5274bc2f950f755f8f63ea9fb74fe8ac056f6889
--- /dev/null
+++ b/consolidated-00193-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b557eaf7684d4f5c4372b5e2b3a719e19fa940118db38954146c8d963d27e7ae
+size 2495933664
diff --git a/consolidated-00194-of-00272.safetensors b/consolidated-00194-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..62ed66640754b9ffd9a03856f6e740f7edfe6088
--- /dev/null
+++ b/consolidated-00194-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abaf658e521a0e6fdb31369eba230606ece4fc1f0fdbfedb5ff5ae1fd74687cc
+size 2495933648
diff --git a/consolidated-00195-of-00272.safetensors b/consolidated-00195-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..046a195eac0a8718ee431e50a3022522e3c5f33d
--- /dev/null
+++ b/consolidated-00195-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252c9531b8d936041ac223754a1e47f225cb384b6d875ade7b88ba3f9bc334ac
+size 2495933656
diff --git a/consolidated-00196-of-00272.safetensors b/consolidated-00196-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9a476de32bd7c5465522e8b286dd11c52540f4e0
--- /dev/null
+++ b/consolidated-00196-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d426fef9ad26efe0cffdfc67e1b4dd3af3466da3da9e0e4f9ea5b973a26c62
+size 2494520568
diff --git a/consolidated-00197-of-00272.safetensors b/consolidated-00197-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca98a2dc9d1344fd4f3c4166f4521f67abe653c8
--- /dev/null
+++ b/consolidated-00197-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4a3d120edfee019b6d05539e41947c07c7334c1dce145ed88a2d331ed360fa
+size 2495933600
diff --git a/consolidated-00198-of-00272.safetensors b/consolidated-00198-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1e38e88a4b5f56f6441bd050772d58a025aaaa4b
--- /dev/null
+++ b/consolidated-00198-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696bf97ef219c0c7f017a0ddf6a124ef979bef6726d0d3fd683c3a9c58343cde
+size 2495933488
diff --git a/consolidated-00199-of-00272.safetensors b/consolidated-00199-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c9a37d2be637536c4cb660815cf38311e1d44df5
--- /dev/null
+++ b/consolidated-00199-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7b392d26c12219e0e178cc4fc46e47320880e47b5b5594b74a30b44849a7f2
+size 2495933480
diff --git a/consolidated-00200-of-00272.safetensors b/consolidated-00200-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b8d99467376c02e4fb64b13445488e23413e40ba
--- /dev/null
+++ b/consolidated-00200-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7bcf79949a98bd4219da0ed6a52d8786ea98dfb95f2de8da44d80f6d06df6b6
+size 2495933488
diff --git a/consolidated-00201-of-00272.safetensors b/consolidated-00201-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6721f910e49ba07e5609dd766eb0fb88595606f4
--- /dev/null
+++ b/consolidated-00201-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0b5493882b2176d7354b97b1688175930e5f8cd67af974da3984ecefc9886c
+size 2494520888
diff --git a/consolidated-00202-of-00272.safetensors b/consolidated-00202-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..08fe3fd0d5ecbb40de4731ccf372ad8b199c71c1
--- /dev/null
+++ b/consolidated-00202-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189a72de78d07026b1df7f206e399e3eddd2a72d749d0da8c089212fd63597a5
+size 2495933704
diff --git a/consolidated-00203-of-00272.safetensors b/consolidated-00203-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6de729ac1ceb1e7246f88dad0b4511b1cbb36e61
--- /dev/null
+++ b/consolidated-00203-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ac28edcb004a7fce032fbdd1376c1efa209d484d1b0ae2829cd991645d816d
+size 2495933656
diff --git a/consolidated-00204-of-00272.safetensors b/consolidated-00204-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f44b0e5f21dfa9ac960e8fb5b515e9e5eac43c1
--- /dev/null
+++ b/consolidated-00204-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f502536425b513d9d59b61cf40f5a0b89b197545db0e997704a47c248f8a078
+size 2495933648
diff --git a/consolidated-00205-of-00272.safetensors b/consolidated-00205-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ea2aabe094d36311c25daa1a2f78007a0332c734
--- /dev/null
+++ b/consolidated-00205-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a815efb4cd09e332f4b969fde9394a28adb5e95d7ab71b4ef3963379a4ad2e43
+size 2494520528
diff --git a/consolidated-00206-of-00272.safetensors b/consolidated-00206-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a5201af7a99ef9df35d971117583ca1e8c06c74b
--- /dev/null
+++ b/consolidated-00206-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0eb14484e90a6cf3de8eeb7075a84d6e317c81e4555c012c75d34ac3c34ce0
+size 2495933816
diff --git a/consolidated-00207-of-00272.safetensors b/consolidated-00207-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1d27a34a3e4a75e4e16b2dd8673ee8f459c1462a
--- /dev/null
+++ b/consolidated-00207-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4e6b80077a36dbec396e1ed9889083fb1fdc0032b8a9701be2a0f5f59c6af9
+size 2495933648
diff --git a/consolidated-00208-of-00272.safetensors b/consolidated-00208-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d934a17a9e77cc2367d843182148cd6bcad79db6
--- /dev/null
+++ b/consolidated-00208-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28608a98334903d27f5f4e25604a41d95af9e0fe1f595149de67358fa39fe42b
+size 2495933656
diff --git a/consolidated-00209-of-00272.safetensors b/consolidated-00209-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c955745496dbd67118a96f5be59d94bb1fcf7226
--- /dev/null
+++ b/consolidated-00209-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534738c43b064f6b65de5bfb8fe7a5eb33d29ff90056589752f213853f5409ac
+size 2495933648
diff --git a/consolidated-00210-of-00272.safetensors b/consolidated-00210-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c705d083bea8d22e157f932b29d8fbebe3d362c6
--- /dev/null
+++ b/consolidated-00210-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0f0564336b903580f902551e18f9cc5a958a323f4d12822fa2bd7edcbe1c23
+size 2494520720
diff --git a/consolidated-00211-of-00272.safetensors b/consolidated-00211-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..94c4d9da52f6646c0fd1dacea8c76448234fc0ec
--- /dev/null
+++ b/consolidated-00211-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4efc1a7217c91f55d299a2e8229e8156f23518471015899a69026dd1c2b0074
+size 2495933752
diff --git a/consolidated-00212-of-00272.safetensors b/consolidated-00212-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77ecf542de99a62db57c99c4bbe6e55bcdc6c915
--- /dev/null
+++ b/consolidated-00212-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81014522b3527cf8bee0f6d3cfb508840ab97d5ad21199ad3ea8ebba2a345e58
+size 2495933656
diff --git a/consolidated-00213-of-00272.safetensors b/consolidated-00213-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..310e671bddbb984a9b3cc910a8dc894b9e919193
--- /dev/null
+++ b/consolidated-00213-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c413737690e03971b0db5bb1efcdd295c369a56d48e51d865662c5ad360a27b
+size 2495933648
diff --git a/consolidated-00214-of-00272.safetensors b/consolidated-00214-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a1b12dd7ac5465be2fb61d532b80af70e4eba094
--- /dev/null
+++ b/consolidated-00214-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21b70945b1d3270ba1de53f83160af35022ef99e9f51e9955d29854acc79da9
+size 2464096800
diff --git a/consolidated-00215-of-00272.safetensors b/consolidated-00215-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b3036dd4660be1630bc5036ac71dc1c0cba9b1f
--- /dev/null
+++ b/consolidated-00215-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75e450855563a6d1d99adda7c1f7f809548ffbbc2373740bc214acacd54fb5c
+size 2496993872
diff --git a/consolidated-00216-of-00272.safetensors b/consolidated-00216-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b8e61596d900ccf8b67560480ea3d32767019863
--- /dev/null
+++ b/consolidated-00216-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ae94396abe538406344fd95b79d7055d64269714ab73fb4ffd6905f4d706b4
+size 2495933696
diff --git a/consolidated-00217-of-00272.safetensors b/consolidated-00217-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5c8d6689b92721cb3317bc5d39e0650071c9d5e4
--- /dev/null
+++ b/consolidated-00217-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6296f00f972c039f1055c9fbd06fb94ad6ed784ebd35c76b749674d47a75cb
+size 2495933656
diff --git a/consolidated-00218-of-00272.safetensors b/consolidated-00218-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ce8ab24eaefdb0845ce886e5c91b804383f78993
--- /dev/null
+++ b/consolidated-00218-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697c12eae00d07694988a6c0059a45ff602d70dddb68382579d1f41d9363016c
+size 2495933648
diff --git a/consolidated-00219-of-00272.safetensors b/consolidated-00219-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17d9bdf047ff66fb158bcfbe209ab464b70edabe
--- /dev/null
+++ b/consolidated-00219-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6c9647d0f24a299c32e26c2a0f49eb253335a8739037142e29f3368c68ffde
+size 2494520568
diff --git a/consolidated-00220-of-00272.safetensors b/consolidated-00220-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1e854ddaad53f1e996f90ceeb04334a82136b233
--- /dev/null
+++ b/consolidated-00220-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd0e96683f933d1b5fe0942d18b1668cf07492731bbdf8dcf48cf3ca0ac1260
+size 2495933800
diff --git a/consolidated-00221-of-00272.safetensors b/consolidated-00221-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c6f6071bfc36a3789c0d353a0cd1fc1533d128a
--- /dev/null
+++ b/consolidated-00221-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcdca68a063f05a2c254f3d679e7b0e5f52437521eadced014c6c834c43e57c
+size 2495933648
diff --git a/consolidated-00222-of-00272.safetensors b/consolidated-00222-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d6538fa2ec9dbd7e1e783dd28707e97ab427fa4
--- /dev/null
+++ b/consolidated-00222-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9136f4d634ea88034b8b0fe373a0d4cd17c5ede90a580a819e1898e51445af6a
+size 2495933656
diff --git a/consolidated-00223-of-00272.safetensors b/consolidated-00223-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f23a78448767b3f623f207b1b8c8f3e95d1dfea7
--- /dev/null
+++ b/consolidated-00223-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f13e37606e87baeb24e30f2c751f841266fc0b7d52188967263dec82fb9409
+size 2495933648
diff --git a/consolidated-00224-of-00272.safetensors b/consolidated-00224-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..07335c00588e9fb859f478c465f22497f29031ea
--- /dev/null
+++ b/consolidated-00224-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b67191dffa8cf50420e9748fe776c1799355a38c1de93e452d7f07e6c9783b
+size 2494520776
diff --git a/consolidated-00225-of-00272.safetensors b/consolidated-00225-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e01a23750a1e7b59e368fb92b57f79df64b43a4c
--- /dev/null
+++ b/consolidated-00225-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effc63ab8f4a3502962359269855f692e362d986cbf1d2d420e3d80c54aa6c60
+size 2495933744
diff --git a/consolidated-00226-of-00272.safetensors b/consolidated-00226-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a451f7682e5aee4dbd31fae800331f68be3076d6
--- /dev/null
+++ b/consolidated-00226-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140221cb31cefdb7caef53a79e49474e99dac3181be3d1e022098d03dde361d9
+size 2495933648
diff --git a/consolidated-00227-of-00272.safetensors b/consolidated-00227-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..37812ecf3ed4d62b9a00d33acfd97cfea8f4fd97
--- /dev/null
+++ b/consolidated-00227-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d5495a964950e943f833793e8886af48567d870b2d6e05da594dc05095b492
+size 2495933656
diff --git a/consolidated-00228-of-00272.safetensors b/consolidated-00228-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..76207fe167b938194cf4cf923f7da67612e14822
--- /dev/null
+++ b/consolidated-00228-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9ab8ccb6a9372d3c0d5729c7fdcd650aee6170ae4f8c27b1eb21095ea7b4e0
+size 2494520448
diff --git a/consolidated-00229-of-00272.safetensors b/consolidated-00229-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3a1f5197b79b68253ad40d60845264aecdb1ce01
--- /dev/null
+++ b/consolidated-00229-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b67cce028163cbd4a25cf6e5e95211f905b763a34aef413a7a10453ecddae8c
+size 2495933800
diff --git a/consolidated-00230-of-00272.safetensors b/consolidated-00230-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..aa678595e300e18e191c9e8cd55772b45aa895da
--- /dev/null
+++ b/consolidated-00230-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249d381df8ba9ffc8e3318ac70ab25fba70eefaaffeab93419675c06a20e4ace
+size 2495933680
diff --git a/consolidated-00231-of-00272.safetensors b/consolidated-00231-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2d370c08539afd200b459d738058c0baa4e1d9c0
--- /dev/null
+++ b/consolidated-00231-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e5e4fbd2f8ffda0953d48f2178646580cceed80e82c7ac99b0c658676f9eb2
+size 2495933648
diff --git a/consolidated-00232-of-00272.safetensors b/consolidated-00232-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1c6bcef929b57055ebd1192971907faa72c36290
--- /dev/null
+++ b/consolidated-00232-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2b4ad76796c16aa53f3e8043427945100373cf8e3b3b47580859d95d41d8de
+size 2495933656
diff --git a/consolidated-00233-of-00272.safetensors b/consolidated-00233-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b7822942c5187d5718eed47f45c966bfd47b5528
--- /dev/null
+++ b/consolidated-00233-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2ddc54695e2da30d0c2961850d2b0fec330fed1afb407ee539623cf190bcab
+size 2494520616
diff --git a/consolidated-00234-of-00272.safetensors b/consolidated-00234-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..25baa98980d6bc717b7a78997ca3bbc465cc55f3
--- /dev/null
+++ b/consolidated-00234-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb8be869883c8b3e26dee8e631c910c8376067b882817885b0bf878605a65af
+size 2495933784
diff --git a/consolidated-00235-of-00272.safetensors b/consolidated-00235-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c8d617b6a88f341d4e6a2aaf85c4093502035417
--- /dev/null
+++ b/consolidated-00235-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fe6d0ca36b739bf70c44d8c97e82dff68b97c4709eaeb207b4a3ff1997f45b
+size 2495933648
diff --git a/consolidated-00236-of-00272.safetensors b/consolidated-00236-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6d05179b8ac7375397fd157bdc11680ea2947c42
--- /dev/null
+++ b/consolidated-00236-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ffbf5c85ced200def640683d8c4c82b0b520e0f74962c4a7e35b7a1ee5387b
+size 2495933648
diff --git a/consolidated-00237-of-00272.safetensors b/consolidated-00237-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cab0e8e35e8dd815643fa48653e9d5e20900d040
--- /dev/null
+++ b/consolidated-00237-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d831987672e9e74f4842b4ddfdc20ca0990ca5a5e7a23c37bdf1914cdd0acdc
+size 2495933656
diff --git a/consolidated-00238-of-00272.safetensors b/consolidated-00238-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2b12aff4b23561b442af5809d64da1903b356a7e
--- /dev/null
+++ b/consolidated-00238-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d338e6e8f255ffb2e9343160154ade4a1e3d20ce5327efcaf8a7501ac56979d4
+size 2494520840
diff --git a/consolidated-00239-of-00272.safetensors b/consolidated-00239-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..aa2170577641f740b4dda69fb5f9ee45937fac63
--- /dev/null
+++ b/consolidated-00239-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58275805d3c03f8a5f92dab8ba150e1c03eda646a90488240ba7c1494374f8cc
+size 2495933728
diff --git a/consolidated-00240-of-00272.safetensors b/consolidated-00240-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b3d3d833085dcdfcd3e84525e8b94bd7e5a1607
--- /dev/null
+++ b/consolidated-00240-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcafa21b1f78fd7a0963aad928278b7c9f64bd819da150e0a2e32bcbe0dc2ad
+size 2495933648
diff --git a/consolidated-00241-of-00272.safetensors b/consolidated-00241-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ac37dd5b0d1275220b48d436e7023e91ff209929
--- /dev/null
+++ b/consolidated-00241-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20211866938cd266492577f3cfb5a43f93504a0cdb2c3eb5ca484ab1ff09e2a
+size 2495933656
diff --git a/consolidated-00242-of-00272.safetensors b/consolidated-00242-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..32f0ba0d7f97df2c003e5347edddba6c0b4060ed
--- /dev/null
+++ b/consolidated-00242-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1180bcc1b9b0a87069b81f54094cfee24b4c139c493efdef7468a86a8080896
+size 2494520472
diff --git a/consolidated-00243-of-00272.safetensors b/consolidated-00243-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fe2a96639f45acf0bf8e4f7c5f79df35acb3747d
--- /dev/null
+++ b/consolidated-00243-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f593dd165a59dcc080b4768b2a5da8233b232092492a8e5de4af2f61c9e3efdb
+size 2495933824
diff --git a/consolidated-00244-of-00272.safetensors b/consolidated-00244-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..09118beca4dca58d1ecac6f0cf800bbc8d494541
--- /dev/null
+++ b/consolidated-00244-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15f92523643580e1b0a764769863af9c8f07fdeaa153c3898ca94faad6ebfbc
+size 2495933664
diff --git a/consolidated-00245-of-00272.safetensors b/consolidated-00245-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..81dd713d08f73951aad2a2a98b383f57a10eb25d
--- /dev/null
+++ b/consolidated-00245-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5044d9b6eaf595ec82d6a53d567c090642efd8ee607e572d03265238460c95f7
+size 2495933648
diff --git a/consolidated-00246-of-00272.safetensors b/consolidated-00246-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d27f72771284603bcc6e17e1c7109d7af7e3705e
--- /dev/null
+++ b/consolidated-00246-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5f3b5fc9b2482acc8dfce2a2201b1ab2f0ece6450f5a61527f948b31488a8d
+size 2495933656
diff --git a/consolidated-00247-of-00272.safetensors b/consolidated-00247-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..155fe2e22b044ded37b2577277aefe9435eddb9b
--- /dev/null
+++ b/consolidated-00247-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60781b6c97b36f90f4a368cc9b59386459837582dfccf9e932368a8383af29e
+size 2494520568
diff --git a/consolidated-00248-of-00272.safetensors b/consolidated-00248-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1b50e338ba64448c4295a852a52792f5e645fe13
--- /dev/null
+++ b/consolidated-00248-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8575349a03b6980c71bd5ac4383a64b09363a960ea562329316d8958401052ae
+size 2495933600
diff --git a/consolidated-00249-of-00272.safetensors b/consolidated-00249-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..681a9c375d097e4455e377129376e9eff1c88eda
--- /dev/null
+++ b/consolidated-00249-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7334c5fe61f18126c2f468c6138226a76a0895ef6008b059c3ed535e066bcf5
+size 2495933488
diff --git a/consolidated-00250-of-00272.safetensors b/consolidated-00250-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..077a3817c27c298c2367e0b8e92381edbf07970d
--- /dev/null
+++ b/consolidated-00250-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7879a098a4b1b6c610fd7a79427dd5b09156fd8f5aa88a28cfdc1a4a38206a4
+size 2495933480
diff --git a/consolidated-00251-of-00272.safetensors b/consolidated-00251-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7d1b1c79af25e043a57cd70df095c2c1767d963
--- /dev/null
+++ b/consolidated-00251-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd06602e427567666e0f9969a214fe873be0cadc1b9086020c9fabe333675b7
+size 2495933488
diff --git a/consolidated-00252-of-00272.safetensors b/consolidated-00252-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e3370fa15945a3273229a2cba81a388eb5338d50
--- /dev/null
+++ b/consolidated-00252-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b8a3ca63df3cac34303c951521446570ae3332ec6a6983320b1ff6ab23f9bc
+size 2494520888
diff --git a/consolidated-00253-of-00272.safetensors b/consolidated-00253-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..876506c6d0d3639635d47846aaf2b130321352af
--- /dev/null
+++ b/consolidated-00253-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a25ad7e409ed42fe7d4e8036efa28d73ee96af5619c4ec3e82aaf54ef6a675
+size 2495933704
diff --git a/consolidated-00254-of-00272.safetensors b/consolidated-00254-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca293e157a4f7125a79098b642e5c988d14ee60d
--- /dev/null
+++ b/consolidated-00254-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2838cb9d5c9d0b8df5912190fb496231f26c43d8a93db3d04ae03e66a3777d04
+size 2495933656
diff --git a/consolidated-00255-of-00272.safetensors b/consolidated-00255-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da3d629bb53159c00383d3ef4204685d79ae4e99
--- /dev/null
+++ b/consolidated-00255-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b9b9948c73a8a557b6e7859c4fcf72c9e339921aff5207bee9109b9d90a55f
+size 2495933648
diff --git a/consolidated-00256-of-00272.safetensors b/consolidated-00256-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..733e673e746f507387f71cb33a78611c799ec600
--- /dev/null
+++ b/consolidated-00256-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6f2263d42fd5559dc10e46d57d5faf5e27485c0eb32907137f3df3a6a6bd95
+size 2494520480
diff --git a/consolidated-00257-of-00272.safetensors b/consolidated-00257-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..676522d7b128f43979742819f88fe8e443eb268f
--- /dev/null
+++ b/consolidated-00257-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3afadbc99e72fcaac96d343ff84a42ea7d792b68f575b74b5cdfba389630e888
+size 2495933648
diff --git a/consolidated-00258-of-00272.safetensors b/consolidated-00258-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a0978c35da0e1fc9260981f4b39686b83b996994
--- /dev/null
+++ b/consolidated-00258-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f833e8362fc0b4b591c78d967eb6b67d9c5bfa5e92c1de0429641dace65710
+size 2495933480
diff --git a/consolidated-00259-of-00272.safetensors b/consolidated-00259-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d02ec14662a6c65f3c88facc99e4131bb58330ff
--- /dev/null
+++ b/consolidated-00259-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff45392e3c4300b87006da8ae37f32f412efe52bfb904a7ab08fd116fd77465a
+size 2495933480
diff --git a/consolidated-00260-of-00272.safetensors b/consolidated-00260-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e7a772fff22be935f1936987b2476328e3aa011
--- /dev/null
+++ b/consolidated-00260-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48cabf7b063078e870c2832fa5e343b828134e70fdc384c986eaffffacfe8ec8
+size 2495933480
diff --git a/consolidated-00261-of-00272.safetensors b/consolidated-00261-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..86dbad3d04102717fb1878a1a3eca8f88c05e1a2
--- /dev/null
+++ b/consolidated-00261-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3144660c943390fc253f8cb9b144c629732eda0c15e071f14398cfae42793c
+size 2494520552
diff --git a/consolidated-00262-of-00272.safetensors b/consolidated-00262-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..74ac0b37b467b223082629da2d54c27fad14b93e
--- /dev/null
+++ b/consolidated-00262-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e841a002849282ab81a466e8a29611d51c8bebd16614d951f235e0d95a0c9a14
+size 2495933584
diff --git a/consolidated-00263-of-00272.safetensors b/consolidated-00263-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d25b41c62aaf0ff4dd0635cfb8af0744ccd0b0b3
--- /dev/null
+++ b/consolidated-00263-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b46b663d908a2e8536f2dd6d29462f3f78f4de5bf07f7d844bd9b6f7409d74
+size 2495933488
diff --git a/consolidated-00264-of-00272.safetensors b/consolidated-00264-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f3e54442fd8f80c53caaf6aef9b80dea086cb04
--- /dev/null
+++ b/consolidated-00264-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee6fe0834502c1f08f4841627bc78cd62d11a51282351bce2e871a39e54796e
+size 2495933480
diff --git a/consolidated-00265-of-00272.safetensors b/consolidated-00265-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a72fc697c6a2463b87b5bd870287dae5c7e350ae
--- /dev/null
+++ b/consolidated-00265-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb14db02d805ca0ac8d0a221ef587b5daf81d65275bda280a8148c48e6304da
+size 2464096624
diff --git a/consolidated-00266-of-00272.safetensors b/consolidated-00266-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..475a571bd8444ee373e7b4a26e9d6cc58c1094bc
--- /dev/null
+++ b/consolidated-00266-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d58e39627d7b15306cf4dcdac0b1e89daf62f78cb55b9b5284f9d361a00b6e
+size 2496993712
diff --git a/consolidated-00267-of-00272.safetensors b/consolidated-00267-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..19626743f3b0da8153b04e0c6fea5725742c74ba
--- /dev/null
+++ b/consolidated-00267-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c92c53d215f9b44302cdf959f6b6d91af0bb6f5ab140aa7669646720270568
+size 2495933528
diff --git a/consolidated-00268-of-00272.safetensors b/consolidated-00268-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f0843763b8151591c2590eedd52d4a255c22aab
--- /dev/null
+++ b/consolidated-00268-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2708839c8f639a589d9ba84f789cd8290c5e01a21a51e98671951221f1ce62d7
+size 2495933488
diff --git a/consolidated-00269-of-00272.safetensors b/consolidated-00269-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cb758ee300e9140065d48a6f1cad0451deff7b59
--- /dev/null
+++ b/consolidated-00269-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ccfb3d8c3d2243211d4fd4e5d85dc81727e541a1a8d4783dc450d28ddae1b2
+size 2495933480
diff --git a/consolidated-00270-of-00272.safetensors b/consolidated-00270-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0f84f8bd9353dc55e2bc25af80630dae2fd46d07
--- /dev/null
+++ b/consolidated-00270-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db470323670195c40fd5796e05bbf5cd38b789ffbdd922dde5804cb86f14219d
+size 1580292152
diff --git a/consolidated-00271-of-00272.safetensors b/consolidated-00271-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a0fa67550e40eb792022ef4f89a71a9db6fefb3
--- /dev/null
+++ b/consolidated-00271-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf75706c5dd3cbd1ae9b69ffdc749e1eac787ad611cfe69af44e4679076f7176
+size 4999447592
diff --git a/consolidated-00272-of-00272.safetensors b/consolidated-00272-of-00272.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b8e7645aa1d3a5b5c584112b75af705b25a9bd9
--- /dev/null
+++ b/consolidated-00272-of-00272.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf2a2bbaf9f8b756b1879b0c12ebcfda9d8057d675603dd379053d2053d34be
+size 3876741776
diff --git a/consolidated.safetensors.index.json b/consolidated.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..768152bfcd07387c46b54999323091e929b92fa2
--- /dev/null
+++ b/consolidated.safetensors.index.json
@@ -0,0 +1,46148 @@
+{
+ "metadata": {
+ "total_size": 681499857920
+ },
+ "weight_map": {
+ "layers.0.attention.kv_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.q_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wkv_a_with_mqa.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wkv_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wkv_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wo.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wo.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wq_a.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wq_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention.wq_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.attention_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.0.feed_forward.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.0.ffn_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.kv_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.q_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wkv_a_with_mqa.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wkv_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wkv_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wo.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wo.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wq_a.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wq_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention.wq_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.attention_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.1.feed_forward.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.1.ffn_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.kv_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.q_a_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wkv_a_with_mqa.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wkv_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wkv_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wo.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wo.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wq_a.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wq_b.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention.wq_b.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.attention_norm.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.0.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.1.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.10.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.100.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.101.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.102.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.103.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.104.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.105.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.106.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.107.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.108.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.109.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w1.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w1.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w2.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w2.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w3.weight": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.11.w3.weight_scale": "consolidated-00001-of-00272.safetensors",
+ "layers.10.experts.110.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.110.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.110.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.110.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.110.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.110.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.111.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.112.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.113.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.114.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.115.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.116.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.117.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.118.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.119.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.12.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.120.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.121.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.122.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.123.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.124.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.125.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.126.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.127.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.13.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.14.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.15.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.16.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.17.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.18.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.19.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.2.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w2.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w2.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w3.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.20.w3.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.21.w1.weight": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.21.w1.weight_scale": "consolidated-00002-of-00272.safetensors",
+ "layers.10.experts.21.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.21.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.21.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.21.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.22.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.23.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.24.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.25.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.26.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.27.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.28.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.29.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.3.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.30.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.31.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.32.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.33.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.34.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.35.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.36.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.37.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.38.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.39.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.4.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.40.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.41.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.42.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.43.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.44.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.45.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w3.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.46.w3.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.47.w1.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.47.w1.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.47.w2.weight": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.47.w2.weight_scale": "consolidated-00003-of-00272.safetensors",
+ "layers.10.experts.47.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.47.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.48.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.49.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.5.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.50.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.51.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.52.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.53.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.54.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.55.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.56.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.57.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.58.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.59.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.6.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.60.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.61.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.62.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.63.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.64.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.65.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.66.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.67.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.68.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.69.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.7.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.70.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.71.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w1.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w1.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w2.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w2.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w3.weight": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.72.w3.weight_scale": "consolidated-00004-of-00272.safetensors",
+ "layers.10.experts.73.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.73.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.73.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.73.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.73.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.73.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.74.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.75.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.76.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.77.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.78.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.79.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.8.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.80.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.81.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.82.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.83.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.84.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.85.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.86.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.87.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.88.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.89.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.9.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.90.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.91.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.92.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.93.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.94.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.95.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.96.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.97.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w2.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w2.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w3.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.98.w3.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.99.w1.weight": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.99.w1.weight_scale": "consolidated-00005-of-00272.safetensors",
+ "layers.10.experts.99.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.experts.99.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.10.experts.99.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.experts.99.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.10.ffn_norm.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.gate.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.10.shared_experts.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.kv_a_norm.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.q_a_norm.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wkv_a_with_mqa.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wkv_b.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wkv_b.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wo.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wo.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wq_a.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wq_b.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention.wq_b.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.attention_norm.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.0.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.1.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.10.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.100.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.101.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.102.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.103.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.104.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.105.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.106.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.107.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.108.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.109.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.11.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.110.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.111.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.112.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.113.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.114.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.115.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.116.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.117.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.118.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w2.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w2.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w3.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.119.w3.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.12.w1.weight": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.12.w1.weight_scale": "consolidated-00006-of-00272.safetensors",
+ "layers.11.experts.12.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.12.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.12.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.12.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.120.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.121.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.122.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.123.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.124.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.125.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.126.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.127.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.13.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.14.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.15.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.16.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.17.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.18.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.19.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.2.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.20.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.21.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.22.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.23.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.24.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.25.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.26.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.27.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.28.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.29.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w3.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.3.w3.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.30.w1.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.30.w1.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.30.w2.weight": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.30.w2.weight_scale": "consolidated-00007-of-00272.safetensors",
+ "layers.11.experts.30.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.30.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.31.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.32.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.33.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.34.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.35.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.36.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.37.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.38.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.39.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.4.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.40.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.41.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.42.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.43.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.44.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.45.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.46.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.47.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.48.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.49.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.5.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.50.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.51.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.52.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.53.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.54.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.55.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w1.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w1.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w2.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w2.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w3.weight": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.56.w3.weight_scale": "consolidated-00008-of-00272.safetensors",
+ "layers.11.experts.57.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.57.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.57.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.57.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.57.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.57.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.58.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.59.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.6.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.60.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.61.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.62.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.63.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.64.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.65.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.66.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.67.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.68.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.69.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.7.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.70.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.71.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.72.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.73.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.74.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.75.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.76.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.77.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.78.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.79.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.8.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.80.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w2.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w2.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w3.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.81.w3.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.82.w1.weight": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.82.w1.weight_scale": "consolidated-00009-of-00272.safetensors",
+ "layers.11.experts.82.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.82.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.82.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.82.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.83.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.84.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.85.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.86.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.87.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.88.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.89.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.9.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.90.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.91.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.92.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.93.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.94.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.95.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.96.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.97.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.98.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.experts.99.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.ffn_norm.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.gate.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.11.shared_experts.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.kv_a_norm.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.q_a_norm.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wkv_a_with_mqa.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wkv_b.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wkv_b.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wo.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wo.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wq_a.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wq_b.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention.wq_b.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.attention_norm.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.0.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.1.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.10.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.100.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.101.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w2.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w2.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w3.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.102.w3.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.103.w1.weight": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.103.w1.weight_scale": "consolidated-00010-of-00272.safetensors",
+ "layers.12.experts.103.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.103.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.103.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.103.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.104.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.105.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.106.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.107.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.108.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.109.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.11.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.110.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.111.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.112.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.113.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.114.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.115.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.116.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.117.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.118.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.119.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.12.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.120.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.121.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.122.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.123.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.124.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.125.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.126.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.127.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w3.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.13.w3.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.14.w1.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.14.w1.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.14.w2.weight": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.14.w2.weight_scale": "consolidated-00011-of-00272.safetensors",
+ "layers.12.experts.14.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.14.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.15.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.16.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.17.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.18.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.19.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.2.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.20.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.21.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.22.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.23.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.24.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.25.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.26.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.27.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.28.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.29.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.3.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.30.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.31.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.32.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.33.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.34.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.35.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.36.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.37.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.38.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.39.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w1.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w1.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w2.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w2.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w3.weight": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.4.w3.weight_scale": "consolidated-00012-of-00272.safetensors",
+ "layers.12.experts.40.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.40.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.40.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.40.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.40.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.40.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.41.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.42.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.43.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.44.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.45.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.46.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.47.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.48.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.49.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.5.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.50.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.51.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.52.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.53.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.54.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.55.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.56.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.57.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.58.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.59.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.6.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.60.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.61.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.62.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.63.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.64.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w2.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w2.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w3.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.65.w3.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.66.w1.weight": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.66.w1.weight_scale": "consolidated-00013-of-00272.safetensors",
+ "layers.12.experts.66.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.66.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.66.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.66.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.67.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.68.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.69.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.7.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.70.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.71.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.72.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.73.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.74.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.75.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.76.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.77.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.78.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.79.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.8.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.80.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.81.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.82.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.83.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.84.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.85.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.86.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.87.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.88.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.89.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.9.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w3.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.90.w3.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.91.w1.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.91.w1.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.91.w2.weight": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.91.w2.weight_scale": "consolidated-00014-of-00272.safetensors",
+ "layers.12.experts.91.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.91.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.92.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.93.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.94.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.95.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.96.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.97.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.98.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.experts.99.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.ffn_norm.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.gate.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.12.shared_experts.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.kv_a_norm.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.q_a_norm.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wkv_a_with_mqa.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wkv_b.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wkv_b.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wo.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wo.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wq_a.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wq_b.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention.wq_b.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.attention_norm.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.0.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.1.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.10.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.100.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.101.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.102.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.103.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.104.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.105.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.106.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.107.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.108.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.109.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.11.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.110.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w3.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.111.w3.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.112.w1.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.112.w1.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.112.w2.weight": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.112.w2.weight_scale": "consolidated-00015-of-00272.safetensors",
+ "layers.13.experts.112.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.112.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.113.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.114.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.115.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.116.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.117.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.118.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.119.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.12.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.120.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.121.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.122.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.123.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.124.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.125.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.126.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.127.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.13.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.14.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.15.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.16.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.17.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.18.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.19.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.2.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.20.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.21.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.22.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w1.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w1.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w2.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w2.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w3.weight": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.23.w3.weight_scale": "consolidated-00016-of-00272.safetensors",
+ "layers.13.experts.24.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.24.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.24.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.24.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.24.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.24.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.25.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.26.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.27.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.28.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.29.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.3.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.30.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.31.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.32.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.33.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.34.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.35.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.36.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.37.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.38.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.39.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.4.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.40.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.41.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.42.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.43.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.44.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.45.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.46.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.47.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.48.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w2.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w2.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w3.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.49.w3.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.5.w1.weight": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.5.w1.weight_scale": "consolidated-00017-of-00272.safetensors",
+ "layers.13.experts.5.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.5.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.5.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.5.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.50.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.51.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.52.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.53.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.54.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.55.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.56.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.57.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.58.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.59.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.6.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.60.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.61.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.62.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.63.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.64.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.65.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.66.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.67.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.68.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.69.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.7.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.70.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.71.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.72.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.73.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w3.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.74.w3.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.75.w1.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.75.w1.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.75.w2.weight": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.75.w2.weight_scale": "consolidated-00018-of-00272.safetensors",
+ "layers.13.experts.75.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.75.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.76.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.77.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.78.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.79.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.8.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.80.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.81.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.82.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.83.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.84.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.85.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.86.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.87.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.88.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.89.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.9.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.90.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.91.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.92.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.93.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.94.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.95.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.96.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.97.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.98.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.experts.99.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.ffn_norm.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.gate.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w1.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w1.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w2.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w2.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w3.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.13.shared_experts.w3.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.kv_a_norm.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.q_a_norm.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.wkv_a_with_mqa.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.wkv_b.weight": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.wkv_b.weight_scale": "consolidated-00019-of-00272.safetensors",
+ "layers.14.attention.wo.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.attention.wo.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.attention.wq_a.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.attention.wq_b.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.attention.wq_b.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.attention_norm.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.0.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.1.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.10.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.100.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.101.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.102.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.103.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.104.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.105.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.106.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.107.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.108.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.109.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.11.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.110.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.111.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.112.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.113.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.114.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.115.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.116.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.117.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.118.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.119.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.12.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w2.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w2.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w3.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.120.w3.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.121.w1.weight": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.121.w1.weight_scale": "consolidated-00020-of-00272.safetensors",
+ "layers.14.experts.121.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.121.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.121.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.121.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.122.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.123.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.124.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.125.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.126.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.127.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.13.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.14.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.15.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.16.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.17.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.18.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.19.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.2.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.20.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.21.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.22.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.23.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.24.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.25.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.26.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.27.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.28.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.29.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.3.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.30.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w3.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.31.w3.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.32.w1.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.32.w1.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.32.w2.weight": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.32.w2.weight_scale": "consolidated-00021-of-00272.safetensors",
+ "layers.14.experts.32.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.32.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.33.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.34.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.35.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.36.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.37.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.38.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.39.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.4.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.40.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.41.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.42.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.43.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.44.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.45.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.46.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.47.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.48.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.49.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.5.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.50.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.51.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.52.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.53.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.54.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.55.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.56.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.57.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w1.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w1.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w2.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w2.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w3.weight": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.58.w3.weight_scale": "consolidated-00022-of-00272.safetensors",
+ "layers.14.experts.59.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.59.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.59.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.59.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.59.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.59.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.6.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.60.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.61.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.62.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.63.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.64.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.65.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.66.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.67.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.68.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.69.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.7.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.70.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.71.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.72.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.73.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.74.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.75.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.76.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.77.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.78.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.79.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.8.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.80.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.81.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.82.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w2.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w2.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w3.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.83.w3.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.84.w1.weight": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.84.w1.weight_scale": "consolidated-00023-of-00272.safetensors",
+ "layers.14.experts.84.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.84.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.84.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.84.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.85.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.86.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.87.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.88.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.89.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.9.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.90.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.91.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.92.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.93.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.94.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.95.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.96.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.97.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.98.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.experts.99.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.ffn_norm.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.gate.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.14.shared_experts.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.kv_a_norm.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.q_a_norm.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wkv_a_with_mqa.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wkv_b.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wkv_b.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wo.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wo.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wq_a.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wq_b.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention.wq_b.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.attention_norm.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.0.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.1.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.10.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.100.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.101.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.102.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.103.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w2.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w2.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w3.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.104.w3.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.105.w1.weight": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.105.w1.weight_scale": "consolidated-00024-of-00272.safetensors",
+ "layers.15.experts.105.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.105.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.105.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.105.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.106.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.107.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.108.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.109.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.11.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.110.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.111.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.112.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.113.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.114.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.115.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.116.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.117.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.118.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.119.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.12.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.120.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.121.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.122.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.123.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.124.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.125.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.126.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.127.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.13.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.14.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w3.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.15.w3.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.16.w1.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.16.w1.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.16.w2.weight": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.16.w2.weight_scale": "consolidated-00025-of-00272.safetensors",
+ "layers.15.experts.16.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.16.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.17.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.18.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.19.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.2.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.20.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.21.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.22.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.23.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.24.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.25.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.26.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.27.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.28.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.29.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.3.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.30.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.31.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.32.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.33.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.34.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.35.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.36.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.37.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.38.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.39.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.4.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.40.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w1.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w1.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w2.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w2.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w3.weight": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.41.w3.weight_scale": "consolidated-00026-of-00272.safetensors",
+ "layers.15.experts.42.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.42.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.42.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.42.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.42.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.42.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.43.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.44.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.45.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.46.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.47.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.48.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.49.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.5.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.50.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.51.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.52.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.53.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.54.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.55.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.56.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.57.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.58.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.59.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.6.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.60.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.61.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.62.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.63.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.64.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.65.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.66.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w2.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w2.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w3.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.67.w3.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.68.w1.weight": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.68.w1.weight_scale": "consolidated-00027-of-00272.safetensors",
+ "layers.15.experts.68.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.68.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.68.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.68.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.69.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.7.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.70.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.71.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.72.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.73.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.74.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.75.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.76.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.77.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.78.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.79.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.8.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.80.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.81.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.82.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.83.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.84.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.85.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.86.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.87.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.88.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.89.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.9.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.90.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.91.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w3.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.92.w3.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.93.w1.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.93.w1.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.93.w2.weight": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.93.w2.weight_scale": "consolidated-00028-of-00272.safetensors",
+ "layers.15.experts.93.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.93.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.94.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.95.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.96.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.97.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.98.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.experts.99.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.ffn_norm.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.gate.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.15.shared_experts.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.kv_a_norm.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.q_a_norm.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wkv_a_with_mqa.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wkv_b.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wkv_b.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wo.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wo.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wq_a.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wq_b.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention.wq_b.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.attention_norm.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.0.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.1.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.10.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.100.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.101.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.102.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.103.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.104.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.105.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.106.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.107.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.108.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.109.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.11.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.110.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.111.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.112.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w3.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.113.w3.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.114.w1.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.114.w1.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.114.w2.weight": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.114.w2.weight_scale": "consolidated-00029-of-00272.safetensors",
+ "layers.16.experts.114.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.114.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.115.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.116.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.117.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.118.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.119.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.12.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.120.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.121.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.122.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.123.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.124.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.125.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.126.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.127.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.13.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.14.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.15.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.16.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.17.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.18.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.19.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.2.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.20.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.21.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.22.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.23.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.24.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w1.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w1.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w2.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w2.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w3.weight": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.25.w3.weight_scale": "consolidated-00030-of-00272.safetensors",
+ "layers.16.experts.26.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.26.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.26.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.26.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.26.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.26.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.27.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.28.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.29.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.3.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.30.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.31.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.32.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.33.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.34.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.35.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.36.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.37.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.38.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.39.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.4.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.40.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.41.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.42.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.43.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.44.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.45.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.46.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.47.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.48.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.49.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.5.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w2.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w2.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w3.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.50.w3.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.51.w1.weight": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.51.w1.weight_scale": "consolidated-00031-of-00272.safetensors",
+ "layers.16.experts.51.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.51.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.51.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.51.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.52.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.53.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.54.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.55.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.56.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.57.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.58.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.59.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.6.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.60.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.61.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.62.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.63.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.64.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.65.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.66.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.67.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.68.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.69.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.7.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.70.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.71.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.72.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.73.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.74.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.75.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w3.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.76.w3.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.77.w1.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.77.w1.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.77.w2.weight": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.77.w2.weight_scale": "consolidated-00032-of-00272.safetensors",
+ "layers.16.experts.77.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.77.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.78.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.79.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.8.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.80.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.81.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.82.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.83.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.84.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.85.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.86.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.87.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.88.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.89.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.9.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.90.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.91.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.92.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.93.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.94.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.95.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.96.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.97.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.98.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.experts.99.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.ffn_norm.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.gate.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w3.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.16.shared_experts.w3.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.kv_a_norm.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.q_a_norm.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wkv_a_with_mqa.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wkv_b.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wkv_b.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wo.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wo.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wq_a.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wq_b.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention.wq_b.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.attention_norm.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.experts.0.w1.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.experts.0.w1.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.experts.0.w2.weight": "consolidated-00033-of-00272.safetensors",
+ "layers.17.experts.0.w2.weight_scale": "consolidated-00033-of-00272.safetensors",
+ "layers.17.experts.0.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.0.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.1.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.10.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.100.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.101.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.102.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.103.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.104.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.105.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.106.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.107.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.108.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.109.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.11.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.110.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.111.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.112.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.113.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.114.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.115.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.116.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.117.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.118.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.119.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.12.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.120.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.121.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.122.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w1.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w1.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w2.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w2.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w3.weight": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.123.w3.weight_scale": "consolidated-00034-of-00272.safetensors",
+ "layers.17.experts.124.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.124.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.124.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.124.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.124.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.124.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.125.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.126.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.127.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.13.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.14.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.15.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.16.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.17.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.18.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.19.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.2.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.20.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.21.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.22.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.23.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.24.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.25.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.26.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.27.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.28.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.29.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.3.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.30.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.31.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.32.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.33.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w2.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w2.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w3.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.34.w3.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.35.w1.weight": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.35.w1.weight_scale": "consolidated-00035-of-00272.safetensors",
+ "layers.17.experts.35.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.35.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.35.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.35.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.36.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.37.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.38.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.39.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.4.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.40.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.41.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.42.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.43.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.44.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.45.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.46.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.47.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.48.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.49.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.5.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.50.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.51.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.52.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.53.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.54.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.55.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.56.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.57.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.58.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.59.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w3.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.6.w3.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.60.w1.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.60.w1.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.60.w2.weight": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.60.w2.weight_scale": "consolidated-00036-of-00272.safetensors",
+ "layers.17.experts.60.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.60.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.61.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.62.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.63.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.64.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.65.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.66.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.67.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.68.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.69.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.7.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.70.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.71.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.72.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.73.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.74.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.75.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.76.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.77.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.78.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.79.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.8.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.80.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.81.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.82.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.83.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.84.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.85.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w1.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w1.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w2.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w2.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w3.weight": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.86.w3.weight_scale": "consolidated-00037-of-00272.safetensors",
+ "layers.17.experts.87.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.87.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.87.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.87.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.87.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.87.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.88.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.89.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.9.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.90.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.91.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.92.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.93.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.94.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.95.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.96.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.97.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.98.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.experts.99.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.ffn_norm.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.gate.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.17.shared_experts.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.kv_a_norm.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.q_a_norm.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wkv_a_with_mqa.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wkv_b.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wkv_b.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wo.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wo.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wq_a.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wq_b.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention.wq_b.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.attention_norm.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.0.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.1.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.10.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.100.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.101.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.102.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.103.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.104.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.105.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.106.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w1.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w1.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w2.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w2.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w3.weight": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.107.w3.weight_scale": "consolidated-00038-of-00272.safetensors",
+ "layers.18.experts.108.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.108.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.108.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.108.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.108.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.108.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.109.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.11.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.110.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.111.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.112.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.113.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.114.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.115.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.116.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.117.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.118.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.119.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.12.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.120.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.121.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.122.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.123.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.124.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.125.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.126.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.127.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.13.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.14.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.15.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.16.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.17.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w2.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w2.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w3.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.18.w3.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.19.w1.weight": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.19.w1.weight_scale": "consolidated-00039-of-00272.safetensors",
+ "layers.18.experts.19.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.19.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.19.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.19.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.2.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.20.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.21.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.22.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.23.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.24.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.25.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.26.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.27.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.28.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.29.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.3.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.30.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.31.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.32.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.33.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.34.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.35.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.36.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.37.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.38.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.39.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.4.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.40.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.41.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.42.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w3.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.43.w3.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.44.w1.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.44.w1.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.44.w2.weight": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.44.w2.weight_scale": "consolidated-00040-of-00272.safetensors",
+ "layers.18.experts.44.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.44.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.45.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.46.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.47.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.48.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.49.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.5.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.50.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.51.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.52.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.53.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.54.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.55.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.56.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.57.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.58.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.59.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.6.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.60.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.61.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.62.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.63.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.64.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.65.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.66.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.67.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.68.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.69.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w1.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w1.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w2.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w2.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w3.weight": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.7.w3.weight_scale": "consolidated-00041-of-00272.safetensors",
+ "layers.18.experts.70.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.70.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.70.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.70.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.70.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.70.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.71.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.72.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.73.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.74.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.75.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.76.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.77.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.78.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.79.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.8.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.80.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.81.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.82.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.83.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.84.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.85.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.86.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.87.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.88.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.89.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.9.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.90.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.91.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.92.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.93.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.94.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w2.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w2.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w3.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.95.w3.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.96.w1.weight": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.96.w1.weight_scale": "consolidated-00042-of-00272.safetensors",
+ "layers.18.experts.96.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.96.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.96.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.96.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.97.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.98.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.experts.99.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.ffn_norm.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.gate.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.18.shared_experts.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.kv_a_norm.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.q_a_norm.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wkv_a_with_mqa.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wkv_b.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wkv_b.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wo.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wo.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wq_a.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wq_b.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention.wq_b.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.attention_norm.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.0.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.1.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.10.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.100.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.101.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.102.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.103.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.104.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.105.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.106.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.107.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.108.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.109.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.11.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.110.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.111.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.112.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.113.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.114.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.115.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w2.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w2.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w3.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.116.w3.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.117.w1.weight": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.117.w1.weight_scale": "consolidated-00043-of-00272.safetensors",
+ "layers.19.experts.117.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.117.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.117.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.117.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.118.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.119.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.12.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.120.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.121.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.122.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.123.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.124.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.125.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.126.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.127.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.13.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.14.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.15.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.16.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.17.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.18.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.19.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.2.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.20.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.21.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.22.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.23.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.24.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.25.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.26.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w3.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.27.w3.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.28.w1.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.28.w1.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.28.w2.weight": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.28.w2.weight_scale": "consolidated-00044-of-00272.safetensors",
+ "layers.19.experts.28.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.28.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.29.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.3.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.30.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.31.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.32.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.33.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.34.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.35.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.36.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.37.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.38.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.39.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.4.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.40.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.41.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.42.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.43.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.44.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.45.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.46.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.47.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.48.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.49.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.5.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.50.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.51.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.52.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w1.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w1.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w2.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w2.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w3.weight": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.53.w3.weight_scale": "consolidated-00045-of-00272.safetensors",
+ "layers.19.experts.54.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.54.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.54.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.54.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.54.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.54.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.55.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.56.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.57.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.58.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.59.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.6.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.60.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.61.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.62.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.63.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.64.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.65.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.66.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.67.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.68.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.69.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.7.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.70.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.71.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.72.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.73.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.74.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.75.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.76.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.77.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.78.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w2.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w2.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w3.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.79.w3.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.8.w1.weight": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.8.w1.weight_scale": "consolidated-00046-of-00272.safetensors",
+ "layers.19.experts.8.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.8.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.8.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.8.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.80.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.81.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.82.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.83.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.84.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.85.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.86.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.87.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.88.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.89.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.9.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.90.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.91.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.92.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.93.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.94.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.95.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.96.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.97.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.98.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.experts.99.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.ffn_norm.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.gate.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w3.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.19.shared_experts.w3.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.kv_a_norm.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.q_a_norm.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wkv_a_with_mqa.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wkv_b.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wkv_b.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wo.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wo.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wq_a.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wq_b.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention.wq_b.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.attention_norm.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.feed_forward.w1.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.feed_forward.w1.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.feed_forward.w2.weight": "consolidated-00047-of-00272.safetensors",
+ "layers.2.feed_forward.w2.weight_scale": "consolidated-00047-of-00272.safetensors",
+ "layers.2.feed_forward.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.2.feed_forward.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.2.ffn_norm.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.kv_a_norm.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.q_a_norm.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wkv_a_with_mqa.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wkv_b.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wkv_b.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wo.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wo.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wq_a.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wq_b.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention.wq_b.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.attention_norm.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.0.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.1.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.10.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.100.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.101.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.102.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.103.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.104.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.105.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.106.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.107.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.108.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.109.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.11.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.110.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.111.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.112.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.113.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.114.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.115.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.116.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.117.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.118.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w3.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.119.w3.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.12.w1.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.12.w1.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.12.w2.weight": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.12.w2.weight_scale": "consolidated-00048-of-00272.safetensors",
+ "layers.20.experts.12.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.12.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.120.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.121.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.122.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.123.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.124.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.125.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.126.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.127.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.13.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.14.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.15.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.16.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.17.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.18.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.19.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.2.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.20.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.21.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.22.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.23.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.24.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.25.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.26.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.27.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.28.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.29.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.3.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w1.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w1.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w2.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w2.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w3.weight": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.30.w3.weight_scale": "consolidated-00049-of-00272.safetensors",
+ "layers.20.experts.31.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.31.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.31.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.31.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.31.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.31.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.32.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.33.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.34.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.35.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.36.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.37.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.38.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.39.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.4.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.40.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.41.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.42.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.43.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.44.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.45.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.46.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.47.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.48.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.49.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.5.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.50.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.51.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.52.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.53.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.54.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.55.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w2.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w2.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w3.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.56.w3.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.57.w1.weight": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.57.w1.weight_scale": "consolidated-00050-of-00272.safetensors",
+ "layers.20.experts.57.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.57.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.57.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.57.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.58.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.59.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.6.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.60.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.61.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.62.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.63.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.64.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.65.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.66.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.67.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.68.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.69.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.7.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.70.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.71.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.72.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.73.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.74.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.75.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.76.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.77.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.78.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.79.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.8.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.80.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w3.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.81.w3.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.82.w1.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.82.w1.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.82.w2.weight": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.82.w2.weight_scale": "consolidated-00051-of-00272.safetensors",
+ "layers.20.experts.82.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.82.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.83.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.84.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.85.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.86.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.87.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.88.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.89.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.9.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.90.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.91.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.92.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.93.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.94.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.95.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.96.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.97.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.98.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.experts.99.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.ffn_norm.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.gate.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.20.shared_experts.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.kv_a_norm.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.q_a_norm.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wkv_a_with_mqa.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wkv_b.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wkv_b.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wo.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wo.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wq_a.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wq_b.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention.wq_b.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.attention_norm.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.0.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.1.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.10.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.100.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.101.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w3.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.102.w3.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.103.w1.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.103.w1.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.103.w2.weight": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.103.w2.weight_scale": "consolidated-00052-of-00272.safetensors",
+ "layers.21.experts.103.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.103.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.104.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.105.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.106.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.107.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.108.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.109.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.11.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.110.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.111.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.112.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.113.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.114.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.115.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.116.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.117.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.118.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.119.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.12.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.120.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.121.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.122.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.123.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.124.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.125.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.126.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.127.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.13.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w1.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w1.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w2.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w2.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w3.weight": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.14.w3.weight_scale": "consolidated-00053-of-00272.safetensors",
+ "layers.21.experts.15.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.15.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.15.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.15.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.15.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.15.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.16.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.17.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.18.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.19.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.2.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.20.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.21.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.22.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.23.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.24.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.25.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.26.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.27.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.28.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.29.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.3.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.30.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.31.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.32.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.33.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.34.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.35.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.36.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.37.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.38.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.39.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w2.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w2.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w3.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.4.w3.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.40.w1.weight": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.40.w1.weight_scale": "consolidated-00054-of-00272.safetensors",
+ "layers.21.experts.40.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.40.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.40.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.40.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.41.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.42.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.43.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.44.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.45.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.46.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.47.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.48.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.49.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.5.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.50.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.51.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.52.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.53.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.54.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.55.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.56.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.57.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.58.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.59.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.6.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.60.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.61.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.62.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.63.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.64.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w3.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.65.w3.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.66.w1.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.66.w1.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.66.w2.weight": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.66.w2.weight_scale": "consolidated-00055-of-00272.safetensors",
+ "layers.21.experts.66.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.66.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.67.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.68.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.69.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.7.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.70.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.71.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.72.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.73.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.74.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.75.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.76.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.77.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.78.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.79.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.8.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.80.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.81.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.82.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.83.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.84.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.85.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.86.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.87.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.88.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.89.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.9.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.90.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w1.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w1.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w2.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w2.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w3.weight": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.91.w3.weight_scale": "consolidated-00056-of-00272.safetensors",
+ "layers.21.experts.92.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.92.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.92.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.92.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.92.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.92.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.93.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.94.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.95.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.96.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.97.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.98.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.experts.99.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.ffn_norm.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.gate.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.21.shared_experts.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.kv_a_norm.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.q_a_norm.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wkv_a_with_mqa.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wkv_b.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wkv_b.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wo.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wo.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wq_a.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wq_b.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention.wq_b.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.attention_norm.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.0.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.1.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.10.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.100.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.101.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.102.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.103.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.104.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.105.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.106.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.107.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.108.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.109.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.11.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.110.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.111.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w1.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w1.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w2.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w2.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w3.weight": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.112.w3.weight_scale": "consolidated-00057-of-00272.safetensors",
+ "layers.22.experts.113.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.113.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.113.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.113.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.113.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.113.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.114.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.115.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.116.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.117.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.118.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.119.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.12.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.120.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.121.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.122.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.123.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.124.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.125.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.126.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.127.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.13.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.14.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.15.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.16.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.17.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.18.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.19.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.2.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.20.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.21.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.22.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w2.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w2.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w3.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.23.w3.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.24.w1.weight": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.24.w1.weight_scale": "consolidated-00058-of-00272.safetensors",
+ "layers.22.experts.24.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.24.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.24.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.24.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.25.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.26.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.27.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.28.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.29.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.3.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.30.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.31.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.32.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.33.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.34.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.35.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.36.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.37.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.38.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.39.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.4.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.40.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.41.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.42.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.43.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.44.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.45.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.46.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.47.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.48.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w3.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.49.w3.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.5.w1.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.5.w1.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.5.w2.weight": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.5.w2.weight_scale": "consolidated-00059-of-00272.safetensors",
+ "layers.22.experts.5.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.5.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.50.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.51.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.52.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.53.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.54.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.55.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.56.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.57.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.58.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.59.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.6.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.60.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.61.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.62.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.63.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.64.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.65.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.66.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.67.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.68.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.69.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.7.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.70.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.71.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.72.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.73.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.74.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w1.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w1.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w2.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w2.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w3.weight": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.75.w3.weight_scale": "consolidated-00060-of-00272.safetensors",
+ "layers.22.experts.76.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.76.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.76.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.76.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.76.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.76.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.77.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.78.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.79.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.8.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.80.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.81.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.82.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.83.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.84.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.85.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.86.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.87.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.88.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.89.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.9.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.90.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.91.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.92.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.93.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.94.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.95.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.96.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.97.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.98.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.experts.99.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.ffn_norm.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.gate.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w1.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w1.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w2.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w2.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w3.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.22.shared_experts.w3.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.kv_a_norm.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.q_a_norm.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.wkv_a_with_mqa.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.wkv_b.weight": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.wkv_b.weight_scale": "consolidated-00061-of-00272.safetensors",
+ "layers.23.attention.wo.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.attention.wo.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.attention.wq_a.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.attention.wq_b.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.attention.wq_b.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.attention_norm.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.0.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.1.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.10.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.100.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.101.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.102.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.103.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.104.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.105.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.106.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.107.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.108.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.109.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.11.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.110.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.111.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.112.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.113.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.114.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.115.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.116.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.117.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.118.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.119.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.12.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w2.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w2.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w3.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.120.w3.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.121.w1.weight": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.121.w1.weight_scale": "consolidated-00062-of-00272.safetensors",
+ "layers.23.experts.121.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.121.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.121.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.121.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.122.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.123.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.124.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.125.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.126.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.127.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.13.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.14.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.15.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.16.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.17.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.18.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.19.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.2.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.20.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.21.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.22.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.23.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.24.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.25.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.26.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.27.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.28.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.29.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.3.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.30.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w3.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.31.w3.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.32.w1.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.32.w1.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.32.w2.weight": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.32.w2.weight_scale": "consolidated-00063-of-00272.safetensors",
+ "layers.23.experts.32.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.32.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.33.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.34.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.35.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.36.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.37.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.38.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.39.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.4.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.40.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.41.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.42.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.43.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.44.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.45.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.46.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.47.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.48.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.49.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.5.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.50.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.51.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.52.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.53.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.54.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.55.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.56.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.57.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w1.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w1.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w2.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w2.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w3.weight": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.58.w3.weight_scale": "consolidated-00064-of-00272.safetensors",
+ "layers.23.experts.59.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.59.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.59.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.59.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.59.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.59.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.6.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.60.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.61.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.62.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.63.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.64.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.65.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.66.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.67.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.68.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.69.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.7.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.70.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.71.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.72.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.73.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.74.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.75.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.76.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.77.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.78.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.79.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.8.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.80.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.81.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.82.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w2.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w2.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w3.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.83.w3.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.84.w1.weight": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.84.w1.weight_scale": "consolidated-00065-of-00272.safetensors",
+ "layers.23.experts.84.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.84.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.84.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.84.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.85.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.86.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.87.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.88.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.89.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.9.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.90.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.91.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.92.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.93.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.94.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.95.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.96.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.97.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.98.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.experts.99.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.ffn_norm.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.gate.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.23.shared_experts.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.kv_a_norm.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.q_a_norm.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wkv_a_with_mqa.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wkv_b.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wkv_b.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wo.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wo.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wq_a.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wq_b.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention.wq_b.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.attention_norm.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.0.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.1.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.10.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.100.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.101.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.102.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.103.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w2.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w2.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w3.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.104.w3.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.105.w1.weight": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.105.w1.weight_scale": "consolidated-00066-of-00272.safetensors",
+ "layers.24.experts.105.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.105.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.105.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.105.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.106.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.107.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.108.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.109.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.11.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.110.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.111.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.112.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.113.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.114.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.115.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.116.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.117.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.118.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.119.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.12.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.120.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.121.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.122.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.123.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.124.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.125.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.126.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.127.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.13.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.14.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w3.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.15.w3.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.16.w1.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.16.w1.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.16.w2.weight": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.16.w2.weight_scale": "consolidated-00067-of-00272.safetensors",
+ "layers.24.experts.16.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.16.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.17.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.18.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.19.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.2.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.20.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.21.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.22.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.23.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.24.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.25.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.26.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.27.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.28.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.29.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.3.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.30.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.31.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.32.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.33.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.34.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.35.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.36.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.37.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.38.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.39.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.4.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.40.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w1.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w1.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w2.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w2.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w3.weight": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.41.w3.weight_scale": "consolidated-00068-of-00272.safetensors",
+ "layers.24.experts.42.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.42.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.42.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.42.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.42.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.42.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.43.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.44.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.45.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.46.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.47.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.48.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.49.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.5.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.50.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.51.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.52.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.53.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.54.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.55.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.56.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.57.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.58.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.59.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.6.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.60.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.61.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.62.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.63.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.64.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.65.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.66.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w2.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w2.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w3.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.67.w3.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.68.w1.weight": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.68.w1.weight_scale": "consolidated-00069-of-00272.safetensors",
+ "layers.24.experts.68.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.68.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.68.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.68.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.69.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.7.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.70.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.71.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.72.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.73.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.74.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.75.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.76.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.77.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.78.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.79.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.8.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.80.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.81.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.82.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.83.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.84.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.85.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.86.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.87.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.88.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.89.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.9.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.90.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.91.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w3.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.92.w3.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.93.w1.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.93.w1.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.93.w2.weight": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.93.w2.weight_scale": "consolidated-00070-of-00272.safetensors",
+ "layers.24.experts.93.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.93.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.94.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.95.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.96.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.97.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.98.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.experts.99.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.ffn_norm.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.gate.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.24.shared_experts.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.kv_a_norm.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.q_a_norm.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wkv_a_with_mqa.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wkv_b.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wkv_b.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wo.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wo.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wq_a.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wq_b.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention.wq_b.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.attention_norm.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.0.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.1.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.10.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.100.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.101.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.102.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.103.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.104.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.105.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.106.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.107.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.108.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.109.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.11.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.110.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.111.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.112.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w3.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.113.w3.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.114.w1.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.114.w1.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.114.w2.weight": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.114.w2.weight_scale": "consolidated-00071-of-00272.safetensors",
+ "layers.25.experts.114.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.114.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.115.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.116.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.117.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.118.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.119.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.12.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.120.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.121.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.122.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.123.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.124.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.125.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.126.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.127.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.13.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.14.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.15.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.16.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.17.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.18.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.19.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.2.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.20.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.21.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.22.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.23.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.24.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w1.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w1.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w2.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w2.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w3.weight": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.25.w3.weight_scale": "consolidated-00072-of-00272.safetensors",
+ "layers.25.experts.26.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.26.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.26.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.26.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.26.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.26.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.27.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.28.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.29.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.3.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.30.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.31.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.32.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.33.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.34.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.35.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.36.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.37.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.38.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.39.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.4.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.40.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.41.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.42.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.43.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.44.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.45.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.46.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.47.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.48.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.49.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.5.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w2.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w2.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w3.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.50.w3.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.51.w1.weight": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.51.w1.weight_scale": "consolidated-00073-of-00272.safetensors",
+ "layers.25.experts.51.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.51.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.51.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.51.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.52.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.53.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.54.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.55.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.56.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.57.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.58.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.59.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.6.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.60.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.61.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.62.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.63.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.64.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.65.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.66.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.67.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.68.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.69.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.7.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.70.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.71.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.72.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.73.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.74.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.75.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w3.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.76.w3.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.77.w1.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.77.w1.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.77.w2.weight": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.77.w2.weight_scale": "consolidated-00074-of-00272.safetensors",
+ "layers.25.experts.77.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.77.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.78.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.79.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.8.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.80.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.81.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.82.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.83.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.84.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.85.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.86.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.87.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.88.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.89.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.9.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.90.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.91.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.92.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.93.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.94.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.95.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.96.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.97.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.98.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.experts.99.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.ffn_norm.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.gate.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w3.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.25.shared_experts.w3.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.kv_a_norm.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.q_a_norm.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wkv_a_with_mqa.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wkv_b.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wkv_b.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wo.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wo.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wq_a.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wq_b.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention.wq_b.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.attention_norm.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.experts.0.w1.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.experts.0.w1.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.experts.0.w2.weight": "consolidated-00075-of-00272.safetensors",
+ "layers.26.experts.0.w2.weight_scale": "consolidated-00075-of-00272.safetensors",
+ "layers.26.experts.0.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.0.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.1.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.10.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.100.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.101.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.102.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.103.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.104.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.105.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.106.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.107.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.108.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.109.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.11.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.110.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.111.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.112.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.113.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.114.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.115.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.116.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.117.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.118.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.119.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.12.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.120.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.121.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.122.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w1.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w1.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w2.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w2.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w3.weight": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.123.w3.weight_scale": "consolidated-00076-of-00272.safetensors",
+ "layers.26.experts.124.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.124.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.124.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.124.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.124.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.124.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.125.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.126.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.127.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.13.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.14.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.15.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.16.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.17.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.18.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.19.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.2.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.20.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.21.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.22.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.23.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.24.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.25.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.26.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.27.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.28.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.29.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.3.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.30.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.31.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.32.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.33.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w2.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w2.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w3.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.34.w3.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.35.w1.weight": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.35.w1.weight_scale": "consolidated-00077-of-00272.safetensors",
+ "layers.26.experts.35.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.35.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.35.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.35.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.36.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.37.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.38.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.39.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.4.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.40.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.41.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.42.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.43.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.44.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.45.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.46.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.47.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.48.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.49.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.5.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.50.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.51.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.52.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.53.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.54.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.55.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.56.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.57.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.58.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.59.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w3.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.6.w3.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.60.w1.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.60.w1.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.60.w2.weight": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.60.w2.weight_scale": "consolidated-00078-of-00272.safetensors",
+ "layers.26.experts.60.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.60.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.61.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.62.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.63.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.64.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.65.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.66.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.67.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.68.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.69.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.7.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.70.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.71.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.72.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.73.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.74.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.75.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.76.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.77.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.78.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.79.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.8.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.80.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.81.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.82.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.83.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.84.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.85.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w1.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w1.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w2.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w2.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w3.weight": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.86.w3.weight_scale": "consolidated-00079-of-00272.safetensors",
+ "layers.26.experts.87.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.87.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.87.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.87.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.87.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.87.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.88.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.89.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.9.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.90.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.91.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.92.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.93.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.94.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.95.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.96.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.97.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.98.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.experts.99.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.ffn_norm.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.gate.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.26.shared_experts.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.kv_a_norm.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.q_a_norm.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wkv_a_with_mqa.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wkv_b.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wkv_b.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wo.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wo.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wq_a.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wq_b.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention.wq_b.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.attention_norm.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.0.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.1.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.10.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.100.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.101.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.102.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.103.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.104.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.105.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.106.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w1.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w1.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w2.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w2.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w3.weight": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.107.w3.weight_scale": "consolidated-00080-of-00272.safetensors",
+ "layers.27.experts.108.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.108.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.108.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.108.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.108.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.108.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.109.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.11.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.110.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.111.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.112.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.113.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.114.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.115.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.116.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.117.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.118.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.119.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.12.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.120.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.121.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.122.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.123.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.124.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.125.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.126.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.127.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.13.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.14.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.15.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.16.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.17.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w2.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w2.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w3.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.18.w3.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.19.w1.weight": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.19.w1.weight_scale": "consolidated-00081-of-00272.safetensors",
+ "layers.27.experts.19.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.19.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.19.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.19.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.2.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.20.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.21.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.22.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.23.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.24.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.25.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.26.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.27.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.28.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.29.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.3.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.30.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.31.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.32.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.33.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.34.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.35.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.36.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.37.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.38.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.39.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.4.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.40.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.41.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.42.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w3.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.43.w3.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.44.w1.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.44.w1.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.44.w2.weight": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.44.w2.weight_scale": "consolidated-00082-of-00272.safetensors",
+ "layers.27.experts.44.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.44.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.45.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.46.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.47.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.48.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.49.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.5.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.50.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.51.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.52.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.53.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.54.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.55.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.56.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.57.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.58.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.59.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.6.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.60.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.61.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.62.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.63.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.64.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.65.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.66.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.67.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.68.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.69.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w1.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w1.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w2.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w2.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w3.weight": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.7.w3.weight_scale": "consolidated-00083-of-00272.safetensors",
+ "layers.27.experts.70.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.70.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.70.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.70.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.70.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.70.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.71.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.72.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.73.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.74.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.75.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.76.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.77.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.78.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.79.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.8.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.80.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.81.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.82.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.83.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.84.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.85.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.86.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.87.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.88.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.89.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.9.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.90.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.91.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.92.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.93.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.94.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w2.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w2.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w3.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.95.w3.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.96.w1.weight": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.96.w1.weight_scale": "consolidated-00084-of-00272.safetensors",
+ "layers.27.experts.96.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.96.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.96.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.96.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.97.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.98.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.experts.99.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.ffn_norm.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.gate.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.27.shared_experts.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.kv_a_norm.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.q_a_norm.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wkv_a_with_mqa.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wkv_b.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wkv_b.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wo.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wo.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wq_a.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wq_b.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention.wq_b.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.attention_norm.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.0.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.1.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.10.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.100.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.101.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.102.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.103.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.104.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.105.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.106.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.107.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.108.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.109.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.11.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.110.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.111.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.112.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.113.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.114.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.115.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w2.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w2.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w3.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.116.w3.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.117.w1.weight": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.117.w1.weight_scale": "consolidated-00085-of-00272.safetensors",
+ "layers.28.experts.117.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.117.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.117.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.117.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.118.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.119.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.12.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.120.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.121.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.122.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.123.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.124.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.125.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.126.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.127.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.13.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.14.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.15.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.16.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.17.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.18.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.19.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.2.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.20.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.21.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.22.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.23.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.24.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.25.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.26.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w3.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.27.w3.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.28.w1.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.28.w1.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.28.w2.weight": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.28.w2.weight_scale": "consolidated-00086-of-00272.safetensors",
+ "layers.28.experts.28.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.28.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.29.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.3.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.30.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.31.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.32.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.33.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.34.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.35.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.36.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.37.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.38.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.39.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.4.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.40.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.41.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.42.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.43.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.44.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.45.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.46.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.47.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.48.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.49.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.5.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.50.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.51.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.52.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w1.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w1.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w2.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w2.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w3.weight": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.53.w3.weight_scale": "consolidated-00087-of-00272.safetensors",
+ "layers.28.experts.54.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.54.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.54.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.54.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.54.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.54.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.55.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.56.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.57.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.58.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.59.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.6.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.60.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.61.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.62.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.63.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.64.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.65.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.66.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.67.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.68.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.69.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.7.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.70.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.71.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.72.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.73.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.74.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.75.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.76.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.77.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.78.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w2.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w2.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w3.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.79.w3.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.8.w1.weight": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.8.w1.weight_scale": "consolidated-00088-of-00272.safetensors",
+ "layers.28.experts.8.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.8.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.8.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.8.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.80.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.81.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.82.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.83.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.84.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.85.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.86.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.87.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.88.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.89.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.9.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.90.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.91.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.92.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.93.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.94.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.95.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.96.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.97.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.98.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.experts.99.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.ffn_norm.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.gate.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.28.shared_experts.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.kv_a_norm.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.q_a_norm.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wkv_a_with_mqa.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wkv_b.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wkv_b.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wo.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wo.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wq_a.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wq_b.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention.wq_b.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.attention_norm.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.0.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.1.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w2.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w2.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w3.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.10.w3.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.100.w1.weight": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.100.w1.weight_scale": "consolidated-00089-of-00272.safetensors",
+ "layers.29.experts.100.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.100.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.100.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.100.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.101.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.102.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.103.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.104.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.105.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.106.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.107.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.108.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.109.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.11.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.110.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.111.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.112.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.113.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.114.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.115.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.116.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.117.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.118.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.119.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.12.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.120.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.121.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.122.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.123.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.124.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w3.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.125.w3.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.126.w1.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.126.w1.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.126.w2.weight": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.126.w2.weight_scale": "consolidated-00090-of-00272.safetensors",
+ "layers.29.experts.126.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.126.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.127.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.13.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.14.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.15.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.16.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.17.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.18.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.19.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.2.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.20.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.21.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.22.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.23.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.24.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.25.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.26.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.27.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.28.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.29.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.3.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.30.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.31.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.32.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.33.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.34.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.35.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.36.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w1.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w1.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w2.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w2.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w3.weight": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.37.w3.weight_scale": "consolidated-00091-of-00272.safetensors",
+ "layers.29.experts.38.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.38.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.38.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.38.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.38.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.38.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.39.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.4.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.40.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.41.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.42.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.43.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.44.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.45.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.46.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.47.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.48.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.49.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.5.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.50.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.51.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.52.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.53.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.54.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.55.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.56.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.57.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.58.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.59.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.6.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.60.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.61.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w2.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w2.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w3.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.62.w3.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.63.w1.weight": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.63.w1.weight_scale": "consolidated-00092-of-00272.safetensors",
+ "layers.29.experts.63.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.63.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.63.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.63.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.64.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.65.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.66.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.67.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.68.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.69.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.7.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.70.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.71.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.72.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.73.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.74.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.75.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.76.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.77.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.78.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.79.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.8.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.80.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.81.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.82.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.83.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.84.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.85.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.86.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.87.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w3.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.88.w3.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.89.w1.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.89.w1.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.89.w2.weight": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.89.w2.weight_scale": "consolidated-00093-of-00272.safetensors",
+ "layers.29.experts.89.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.89.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.9.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.90.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.91.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.92.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.93.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.94.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.95.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.96.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.97.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.98.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.experts.99.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.ffn_norm.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.gate.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.29.shared_experts.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.kv_a_norm.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.q_a_norm.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wkv_a_with_mqa.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wkv_b.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wkv_b.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wo.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wo.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wq_a.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wq_b.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention.wq_b.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.attention_norm.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.0.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.1.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.10.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.100.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.101.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.102.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.103.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.104.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.105.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.106.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.107.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.108.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w3.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.109.w3.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.11.w1.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.11.w1.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.11.w2.weight": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.11.w2.weight_scale": "consolidated-00094-of-00272.safetensors",
+ "layers.3.experts.11.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.11.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.110.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.111.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.112.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.113.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.114.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.115.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.116.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.117.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.118.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.119.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.12.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.120.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.121.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.122.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.123.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.124.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.125.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.126.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.127.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.13.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.14.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.15.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.16.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.17.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.18.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.19.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.2.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w1.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w1.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w2.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w2.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w3.weight": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.20.w3.weight_scale": "consolidated-00095-of-00272.safetensors",
+ "layers.3.experts.21.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.21.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.21.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.21.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.21.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.21.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.22.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.23.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.24.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.25.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.26.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.27.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.28.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.29.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.3.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.30.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.31.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.32.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.33.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.34.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.35.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.36.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.37.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.38.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.39.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.4.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.40.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.41.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.42.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.43.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.44.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.45.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w2.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w2.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w3.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.46.w3.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.47.w1.weight": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.47.w1.weight_scale": "consolidated-00096-of-00272.safetensors",
+ "layers.3.experts.47.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.47.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.47.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.47.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.48.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.49.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.5.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.50.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.51.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.52.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.53.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.54.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.55.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.56.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.57.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.58.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.59.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.6.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.60.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.61.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.62.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.63.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.64.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.65.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.66.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.67.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.68.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.69.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.7.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.70.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w3.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.71.w3.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.72.w1.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.72.w1.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.72.w2.weight": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.72.w2.weight_scale": "consolidated-00097-of-00272.safetensors",
+ "layers.3.experts.72.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.72.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.73.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.74.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.75.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.76.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.77.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.78.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.79.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.8.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.80.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.81.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.82.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.83.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.84.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.85.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.86.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.87.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.88.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.89.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.9.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.90.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.91.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.92.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.93.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.94.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.95.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.96.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.97.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w1.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w1.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w2.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w2.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w3.weight": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.98.w3.weight_scale": "consolidated-00098-of-00272.safetensors",
+ "layers.3.experts.99.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.experts.99.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.3.experts.99.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.experts.99.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.3.experts.99.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.experts.99.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.3.ffn_norm.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.gate.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.3.shared_experts.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.kv_a_norm.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.q_a_norm.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wkv_a_with_mqa.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wkv_b.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wkv_b.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wo.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wo.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wq_a.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wq_b.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention.wq_b.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.attention_norm.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.0.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.1.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.10.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.100.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.101.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.102.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.103.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.104.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.105.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.106.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.107.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.108.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.109.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.11.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.110.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.111.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.112.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.113.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.114.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.115.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.116.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.117.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.118.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w1.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w1.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w2.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w2.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w3.weight": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.119.w3.weight_scale": "consolidated-00099-of-00272.safetensors",
+ "layers.30.experts.12.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.12.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.12.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.12.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.12.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.12.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.120.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.121.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.122.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.123.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.124.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.125.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.126.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.127.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.13.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.14.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.15.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.16.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.17.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.18.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.19.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.2.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.20.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.21.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.22.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.23.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.24.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.25.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.26.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.27.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.28.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.29.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w2.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w2.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w3.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.3.w3.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.30.w1.weight": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.30.w1.weight_scale": "consolidated-00100-of-00272.safetensors",
+ "layers.30.experts.30.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.30.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.30.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.30.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.31.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.32.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.33.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.34.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.35.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.36.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.37.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.38.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.39.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.4.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.40.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.41.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.42.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.43.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.44.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.45.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.46.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.47.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.48.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.49.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.5.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.50.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.51.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.52.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.53.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.54.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w3.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.55.w3.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.56.w1.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.56.w1.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.56.w2.weight": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.56.w2.weight_scale": "consolidated-00101-of-00272.safetensors",
+ "layers.30.experts.56.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.56.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.57.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.58.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.59.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.6.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.60.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.61.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.62.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.63.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.64.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.65.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.66.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.67.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.68.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.69.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.7.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.70.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.71.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.72.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.73.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.74.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.75.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.76.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.77.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.78.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.79.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.8.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.80.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w1.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w1.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w2.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w2.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w3.weight": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.81.w3.weight_scale": "consolidated-00102-of-00272.safetensors",
+ "layers.30.experts.82.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.82.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.82.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.82.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.82.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.82.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.83.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.84.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.85.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.86.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.87.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.88.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.89.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.9.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.90.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.91.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.92.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.93.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.94.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.95.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.96.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.97.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.98.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.experts.99.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.ffn_norm.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.gate.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.30.shared_experts.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.kv_a_norm.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.q_a_norm.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wkv_a_with_mqa.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wkv_b.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wkv_b.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wo.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wo.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wq_a.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wq_b.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention.wq_b.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.attention_norm.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.0.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.1.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.10.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.100.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.101.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w1.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w1.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w2.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w2.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w3.weight": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.102.w3.weight_scale": "consolidated-00103-of-00272.safetensors",
+ "layers.31.experts.103.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.103.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.103.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.103.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.103.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.103.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.104.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.105.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.106.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.107.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.108.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.109.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.11.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.110.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.111.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.112.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.113.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.114.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.115.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.116.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.117.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.118.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.119.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.12.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.120.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.121.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.122.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.123.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.124.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.125.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.126.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.127.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w2.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w2.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w3.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.13.w3.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.14.w1.weight": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.14.w1.weight_scale": "consolidated-00104-of-00272.safetensors",
+ "layers.31.experts.14.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.14.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.14.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.14.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.15.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.16.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.17.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.18.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.19.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.2.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.20.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.21.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.22.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.23.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.24.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.25.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.26.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.27.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.28.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.29.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.3.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.30.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.31.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.32.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.33.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.34.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.35.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.36.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.37.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.38.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w3.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.39.w3.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.4.w1.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.4.w1.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.4.w2.weight": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.4.w2.weight_scale": "consolidated-00105-of-00272.safetensors",
+ "layers.31.experts.4.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.4.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.40.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.41.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.42.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.43.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.44.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.45.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.46.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.47.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.48.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.49.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.5.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.50.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.51.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.52.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.53.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.54.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.55.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.56.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.57.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.58.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.59.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.6.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.60.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.61.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.62.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.63.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.64.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w1.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w1.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w2.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w2.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w3.weight": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.65.w3.weight_scale": "consolidated-00106-of-00272.safetensors",
+ "layers.31.experts.66.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.66.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.66.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.66.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.66.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.66.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.67.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.68.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.69.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.7.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.70.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.71.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.72.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.73.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.74.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.75.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.76.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.77.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.78.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.79.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.8.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.80.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.81.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.82.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.83.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.84.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.85.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.86.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.87.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.88.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.89.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.9.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w2.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w2.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w3.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.90.w3.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.91.w1.weight": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.91.w1.weight_scale": "consolidated-00107-of-00272.safetensors",
+ "layers.31.experts.91.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.91.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.91.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.91.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.92.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.93.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.94.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.95.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.96.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.97.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.98.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.experts.99.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.ffn_norm.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.gate.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.31.shared_experts.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.kv_a_norm.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.q_a_norm.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wkv_a_with_mqa.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wkv_b.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wkv_b.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wo.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wo.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wq_a.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wq_b.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention.wq_b.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.attention_norm.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.0.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.1.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.10.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.100.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.101.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.102.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.103.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.104.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.105.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.106.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.107.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.108.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.109.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.11.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.110.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w2.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w2.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w3.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.111.w3.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.112.w1.weight": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.112.w1.weight_scale": "consolidated-00108-of-00272.safetensors",
+ "layers.32.experts.112.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.112.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.112.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.112.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.113.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.114.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.115.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.116.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.117.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.118.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.119.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.12.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.120.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.121.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.122.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.123.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.124.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.125.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.126.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.127.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.13.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.14.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.15.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.16.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.17.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.18.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.19.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.2.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.20.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.21.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w3.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.22.w3.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.23.w1.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.23.w1.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.23.w2.weight": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.23.w2.weight_scale": "consolidated-00109-of-00272.safetensors",
+ "layers.32.experts.23.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.23.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.24.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.25.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.26.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.27.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.28.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.29.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.3.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.30.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.31.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.32.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.33.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.34.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.35.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.36.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.37.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.38.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.39.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.4.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.40.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.41.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.42.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.43.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.44.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.45.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.46.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.47.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.48.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w1.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w1.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w2.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w2.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w3.weight": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.49.w3.weight_scale": "consolidated-00110-of-00272.safetensors",
+ "layers.32.experts.5.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.5.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.5.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.5.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.5.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.5.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.50.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.51.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.52.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.53.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.54.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.55.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.56.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.57.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.58.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.59.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.6.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.60.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.61.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.62.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.63.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.64.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.65.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.66.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.67.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.68.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.69.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.7.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.70.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.71.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.72.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.73.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w2.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w2.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w3.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.74.w3.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.75.w1.weight": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.75.w1.weight_scale": "consolidated-00111-of-00272.safetensors",
+ "layers.32.experts.75.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.75.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.75.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.75.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.76.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.77.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.78.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.79.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.8.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.80.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.81.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.82.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.83.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.84.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.85.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.86.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.87.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.88.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.89.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.9.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.90.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.91.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.92.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.93.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.94.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.95.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.96.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.97.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.98.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.experts.99.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.ffn_norm.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.gate.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w1.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w1.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w2.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w2.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w3.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.32.shared_experts.w3.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.kv_a_norm.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.q_a_norm.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.wkv_a_with_mqa.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.wkv_b.weight": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.wkv_b.weight_scale": "consolidated-00112-of-00272.safetensors",
+ "layers.33.attention.wo.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.attention.wo.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.attention.wq_a.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.attention.wq_b.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.attention.wq_b.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.attention_norm.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.0.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.1.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.10.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.100.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.101.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.102.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.103.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.104.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.105.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.106.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.107.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.108.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.109.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.11.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.110.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.111.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.112.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.113.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.114.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.115.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.116.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.117.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.118.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.119.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.12.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w2.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w2.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w3.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.120.w3.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.121.w1.weight": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.121.w1.weight_scale": "consolidated-00113-of-00272.safetensors",
+ "layers.33.experts.121.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.121.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.121.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.121.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.122.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.123.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.124.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.125.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.126.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.127.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.13.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.14.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.15.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.16.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.17.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.18.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.19.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.2.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.20.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.21.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.22.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.23.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.24.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.25.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.26.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.27.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.28.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.29.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.3.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.30.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w3.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.31.w3.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.32.w1.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.32.w1.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.32.w2.weight": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.32.w2.weight_scale": "consolidated-00114-of-00272.safetensors",
+ "layers.33.experts.32.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.32.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.33.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.34.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.35.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.36.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.37.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.38.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.39.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.4.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.40.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.41.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.42.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.43.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.44.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.45.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.46.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.47.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.48.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.49.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.5.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.50.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.51.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.52.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.53.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.54.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.55.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.56.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.57.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w1.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w1.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w2.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w2.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w3.weight": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.58.w3.weight_scale": "consolidated-00115-of-00272.safetensors",
+ "layers.33.experts.59.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.59.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.59.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.59.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.59.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.59.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.6.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.60.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.61.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.62.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.63.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.64.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.65.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.66.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.67.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.68.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.69.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.7.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.70.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.71.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.72.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.73.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.74.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.75.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.76.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.77.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.78.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.79.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.8.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.80.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.81.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.82.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w2.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w2.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w3.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.83.w3.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.84.w1.weight": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.84.w1.weight_scale": "consolidated-00116-of-00272.safetensors",
+ "layers.33.experts.84.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.84.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.84.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.84.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.85.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.86.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.87.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.88.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.89.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.9.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.90.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.91.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.92.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.93.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.94.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.95.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.96.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.97.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.98.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.experts.99.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.ffn_norm.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.gate.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.33.shared_experts.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.kv_a_norm.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.q_a_norm.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wkv_a_with_mqa.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wkv_b.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wkv_b.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wo.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wo.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wq_a.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wq_b.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention.wq_b.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.attention_norm.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.0.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.1.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.10.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.100.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.101.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.102.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.103.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w2.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w2.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w3.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.104.w3.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.105.w1.weight": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.105.w1.weight_scale": "consolidated-00117-of-00272.safetensors",
+ "layers.34.experts.105.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.105.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.105.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.105.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.106.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.107.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.108.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.109.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.11.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.110.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.111.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.112.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.113.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.114.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.115.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.116.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.117.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.118.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.119.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.12.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.120.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.121.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.122.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.123.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.124.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.125.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.126.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.127.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.13.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.14.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w3.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.15.w3.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.16.w1.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.16.w1.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.16.w2.weight": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.16.w2.weight_scale": "consolidated-00118-of-00272.safetensors",
+ "layers.34.experts.16.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.16.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.17.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.18.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.19.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.2.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.20.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.21.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.22.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.23.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.24.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.25.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.26.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.27.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.28.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.29.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.3.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.30.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.31.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.32.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.33.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.34.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.35.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.36.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.37.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.38.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.39.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.4.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.40.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w1.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w1.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w2.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w2.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w3.weight": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.41.w3.weight_scale": "consolidated-00119-of-00272.safetensors",
+ "layers.34.experts.42.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.42.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.42.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.42.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.42.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.42.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.43.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.44.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.45.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.46.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.47.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.48.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.49.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.5.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.50.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.51.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.52.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.53.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.54.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.55.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.56.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.57.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.58.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.59.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.6.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.60.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.61.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.62.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.63.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.64.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.65.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.66.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w2.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w2.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w3.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.67.w3.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.68.w1.weight": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.68.w1.weight_scale": "consolidated-00120-of-00272.safetensors",
+ "layers.34.experts.68.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.68.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.68.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.68.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.69.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.7.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.70.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.71.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.72.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.73.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.74.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.75.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.76.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.77.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.78.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.79.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.8.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.80.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.81.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.82.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.83.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.84.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.85.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.86.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.87.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.88.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.89.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.9.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.90.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.91.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w3.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.92.w3.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.93.w1.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.93.w1.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.93.w2.weight": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.93.w2.weight_scale": "consolidated-00121-of-00272.safetensors",
+ "layers.34.experts.93.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.93.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.94.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.95.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.96.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.97.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.98.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.experts.99.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.ffn_norm.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.gate.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.34.shared_experts.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.kv_a_norm.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.q_a_norm.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wkv_a_with_mqa.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wkv_b.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wkv_b.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wo.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wo.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wq_a.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wq_b.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention.wq_b.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.attention_norm.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.0.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.1.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.10.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.100.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.101.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.102.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.103.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.104.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.105.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.106.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.107.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.108.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.109.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.11.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.110.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.111.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.112.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w3.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.113.w3.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.114.w1.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.114.w1.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.114.w2.weight": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.114.w2.weight_scale": "consolidated-00122-of-00272.safetensors",
+ "layers.35.experts.114.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.114.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.115.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.116.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.117.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.118.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.119.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.12.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.120.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.121.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.122.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.123.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.124.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.125.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.126.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.127.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.13.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.14.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.15.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.16.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.17.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.18.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.19.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.2.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.20.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.21.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.22.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.23.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.24.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w1.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w1.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w2.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w2.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w3.weight": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.25.w3.weight_scale": "consolidated-00123-of-00272.safetensors",
+ "layers.35.experts.26.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.26.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.26.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.26.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.26.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.26.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.27.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.28.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.29.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.3.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.30.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.31.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.32.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.33.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.34.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.35.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.36.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.37.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.38.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.39.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.4.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.40.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.41.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.42.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.43.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.44.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.45.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.46.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.47.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.48.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.49.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.5.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w2.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w2.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w3.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.50.w3.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.51.w1.weight": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.51.w1.weight_scale": "consolidated-00124-of-00272.safetensors",
+ "layers.35.experts.51.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.51.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.51.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.51.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.52.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.53.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.54.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.55.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.56.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.57.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.58.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.59.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.6.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.60.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.61.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.62.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.63.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.64.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.65.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.66.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.67.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.68.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.69.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.7.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.70.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.71.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.72.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.73.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.74.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.75.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w3.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.76.w3.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.77.w1.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.77.w1.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.77.w2.weight": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.77.w2.weight_scale": "consolidated-00125-of-00272.safetensors",
+ "layers.35.experts.77.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.77.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.78.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.79.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.8.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.80.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.81.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.82.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.83.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.84.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.85.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.86.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.87.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.88.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.89.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.9.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.90.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.91.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.92.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.93.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.94.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.95.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.96.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.97.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.98.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.experts.99.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.ffn_norm.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.gate.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w3.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.35.shared_experts.w3.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.kv_a_norm.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.q_a_norm.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wkv_a_with_mqa.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wkv_b.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wkv_b.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wo.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wo.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wq_a.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wq_b.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention.wq_b.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.attention_norm.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.experts.0.w1.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.experts.0.w1.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.experts.0.w2.weight": "consolidated-00126-of-00272.safetensors",
+ "layers.36.experts.0.w2.weight_scale": "consolidated-00126-of-00272.safetensors",
+ "layers.36.experts.0.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.0.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.1.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.10.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.100.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.101.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.102.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.103.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.104.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.105.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.106.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.107.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.108.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.109.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.11.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.110.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.111.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.112.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.113.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.114.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.115.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.116.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.117.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.118.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.119.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.12.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.120.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.121.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.122.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w1.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w1.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w2.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w2.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w3.weight": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.123.w3.weight_scale": "consolidated-00127-of-00272.safetensors",
+ "layers.36.experts.124.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.124.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.124.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.124.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.124.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.124.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.125.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.126.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.127.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.13.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.14.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.15.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.16.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.17.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.18.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.19.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.2.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.20.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.21.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.22.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.23.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.24.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.25.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.26.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.27.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.28.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.29.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.3.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.30.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.31.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.32.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.33.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w2.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w2.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w3.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.34.w3.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.35.w1.weight": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.35.w1.weight_scale": "consolidated-00128-of-00272.safetensors",
+ "layers.36.experts.35.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.35.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.35.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.35.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.36.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.37.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.38.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.39.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.4.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.40.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.41.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.42.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.43.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.44.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.45.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.46.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.47.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.48.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.49.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.5.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.50.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.51.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.52.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.53.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.54.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.55.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.56.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.57.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.58.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.59.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w3.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.6.w3.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.60.w1.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.60.w1.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.60.w2.weight": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.60.w2.weight_scale": "consolidated-00129-of-00272.safetensors",
+ "layers.36.experts.60.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.60.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.61.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.62.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.63.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.64.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.65.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.66.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.67.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.68.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.69.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.7.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.70.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.71.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.72.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.73.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.74.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.75.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.76.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.77.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.78.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.79.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.8.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.80.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.81.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.82.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.83.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.84.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.85.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w1.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w1.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w2.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w2.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w3.weight": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.86.w3.weight_scale": "consolidated-00130-of-00272.safetensors",
+ "layers.36.experts.87.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.87.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.87.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.87.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.87.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.87.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.88.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.89.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.9.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.90.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.91.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.92.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.93.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.94.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.95.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.96.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.97.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.98.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.experts.99.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.ffn_norm.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.gate.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.36.shared_experts.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.kv_a_norm.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.q_a_norm.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wkv_a_with_mqa.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wkv_b.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wkv_b.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wo.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wo.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wq_a.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wq_b.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention.wq_b.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.attention_norm.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.0.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.1.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.10.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.100.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.101.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.102.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.103.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.104.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.105.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.106.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w1.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w1.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w2.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w2.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w3.weight": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.107.w3.weight_scale": "consolidated-00131-of-00272.safetensors",
+ "layers.37.experts.108.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.108.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.108.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.108.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.108.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.108.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.109.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.11.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.110.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.111.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.112.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.113.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.114.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.115.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.116.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.117.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.118.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.119.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.12.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.120.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.121.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.122.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.123.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.124.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.125.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.126.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.127.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.13.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.14.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.15.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.16.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.17.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w2.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w2.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w3.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.18.w3.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.19.w1.weight": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.19.w1.weight_scale": "consolidated-00132-of-00272.safetensors",
+ "layers.37.experts.19.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.19.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.19.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.19.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.2.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.20.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.21.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.22.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.23.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.24.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.25.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.26.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.27.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.28.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.29.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.3.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.30.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.31.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.32.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.33.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.34.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.35.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.36.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.37.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.38.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.39.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.4.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.40.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.41.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.42.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w3.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.43.w3.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.44.w1.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.44.w1.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.44.w2.weight": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.44.w2.weight_scale": "consolidated-00133-of-00272.safetensors",
+ "layers.37.experts.44.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.44.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.45.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.46.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.47.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.48.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.49.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.5.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.50.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.51.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.52.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.53.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.54.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.55.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.56.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.57.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.58.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.59.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.6.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.60.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.61.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.62.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.63.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.64.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.65.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.66.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.67.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.68.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.69.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w1.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w1.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w2.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w2.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w3.weight": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.7.w3.weight_scale": "consolidated-00134-of-00272.safetensors",
+ "layers.37.experts.70.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.70.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.70.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.70.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.70.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.70.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.71.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.72.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.73.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.74.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.75.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.76.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.77.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.78.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.79.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.8.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.80.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.81.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.82.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.83.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.84.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.85.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.86.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.87.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.88.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.89.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.9.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.90.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.91.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.92.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.93.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.94.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w2.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w2.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w3.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.95.w3.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.96.w1.weight": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.96.w1.weight_scale": "consolidated-00135-of-00272.safetensors",
+ "layers.37.experts.96.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.96.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.96.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.96.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.97.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.98.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.experts.99.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.ffn_norm.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.gate.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.37.shared_experts.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.kv_a_norm.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.q_a_norm.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wkv_a_with_mqa.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wkv_b.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wkv_b.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wo.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wo.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wq_a.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wq_b.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention.wq_b.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.attention_norm.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.0.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.1.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.10.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.100.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.101.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.102.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.103.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.104.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.105.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.106.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.107.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.108.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.109.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.11.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.110.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.111.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.112.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.113.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.114.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.115.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w2.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w2.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w3.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.116.w3.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.117.w1.weight": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.117.w1.weight_scale": "consolidated-00136-of-00272.safetensors",
+ "layers.38.experts.117.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.117.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.117.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.117.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.118.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.119.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.12.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.120.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.121.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.122.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.123.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.124.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.125.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.126.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.127.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.13.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.14.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.15.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.16.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.17.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.18.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.19.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.2.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.20.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.21.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.22.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.23.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.24.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.25.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.26.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w3.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.27.w3.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.28.w1.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.28.w1.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.28.w2.weight": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.28.w2.weight_scale": "consolidated-00137-of-00272.safetensors",
+ "layers.38.experts.28.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.28.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.29.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.3.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.30.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.31.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.32.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.33.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.34.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.35.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.36.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.37.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.38.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.39.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.4.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.40.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.41.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.42.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.43.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.44.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.45.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.46.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.47.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.48.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.49.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.5.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.50.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.51.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.52.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w1.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w1.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w2.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w2.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w3.weight": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.53.w3.weight_scale": "consolidated-00138-of-00272.safetensors",
+ "layers.38.experts.54.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.54.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.54.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.54.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.54.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.54.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.55.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.56.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.57.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.58.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.59.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.6.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.60.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.61.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.62.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.63.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.64.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.65.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.66.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.67.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.68.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.69.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.7.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.70.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.71.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.72.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.73.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.74.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.75.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.76.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.77.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.78.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w2.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w2.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w3.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.79.w3.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.8.w1.weight": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.8.w1.weight_scale": "consolidated-00139-of-00272.safetensors",
+ "layers.38.experts.8.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.8.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.8.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.8.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.80.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.81.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.82.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.83.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.84.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.85.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.86.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.87.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.88.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.89.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.9.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.90.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.91.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.92.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.93.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.94.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.95.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.96.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.97.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.98.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.experts.99.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.ffn_norm.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.gate.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.38.shared_experts.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.kv_a_norm.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.q_a_norm.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wkv_a_with_mqa.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wkv_b.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wkv_b.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wo.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wo.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wq_a.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wq_b.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention.wq_b.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.attention_norm.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.0.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.1.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w2.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w2.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w3.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.10.w3.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.100.w1.weight": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.100.w1.weight_scale": "consolidated-00140-of-00272.safetensors",
+ "layers.39.experts.100.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.100.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.100.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.100.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.101.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.102.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.103.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.104.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.105.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.106.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.107.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.108.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.109.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.11.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.110.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.111.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.112.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.113.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.114.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.115.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.116.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.117.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.118.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.119.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.12.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.120.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.121.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.122.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.123.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.124.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w3.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.125.w3.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.126.w1.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.126.w1.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.126.w2.weight": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.126.w2.weight_scale": "consolidated-00141-of-00272.safetensors",
+ "layers.39.experts.126.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.126.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.127.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.13.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.14.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.15.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.16.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.17.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.18.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.19.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.2.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.20.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.21.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.22.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.23.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.24.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.25.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.26.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.27.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.28.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.29.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.3.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.30.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.31.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.32.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.33.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.34.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.35.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.36.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w1.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w1.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w2.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w2.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w3.weight": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.37.w3.weight_scale": "consolidated-00142-of-00272.safetensors",
+ "layers.39.experts.38.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.38.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.38.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.38.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.38.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.38.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.39.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.4.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.40.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.41.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.42.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.43.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.44.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.45.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.46.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.47.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.48.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.49.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.5.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.50.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.51.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.52.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.53.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.54.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.55.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.56.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.57.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.58.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.59.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.6.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.60.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.61.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w2.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w2.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w3.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.62.w3.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.63.w1.weight": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.63.w1.weight_scale": "consolidated-00143-of-00272.safetensors",
+ "layers.39.experts.63.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.63.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.63.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.63.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.64.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.65.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.66.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.67.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.68.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.69.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.7.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.70.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.71.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.72.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.73.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.74.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.75.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.76.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.77.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.78.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.79.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.8.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.80.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.81.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.82.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.83.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.84.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.85.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.86.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.87.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w3.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.88.w3.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.89.w1.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.89.w1.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.89.w2.weight": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.89.w2.weight_scale": "consolidated-00144-of-00272.safetensors",
+ "layers.39.experts.89.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.89.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.9.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.90.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.91.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.92.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.93.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.94.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.95.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.96.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.97.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.98.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.experts.99.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.ffn_norm.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.gate.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.39.shared_experts.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.kv_a_norm.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.q_a_norm.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wkv_a_with_mqa.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wkv_b.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wkv_b.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wo.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wo.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wq_a.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wq_b.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention.wq_b.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.attention_norm.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.0.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.1.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.10.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.100.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.101.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.102.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.103.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.104.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.105.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.106.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.107.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.108.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w3.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.109.w3.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.11.w1.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.11.w1.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.11.w2.weight": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.11.w2.weight_scale": "consolidated-00145-of-00272.safetensors",
+ "layers.4.experts.11.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.11.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.110.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.111.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.112.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.113.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.114.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.115.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.116.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.117.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.118.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.119.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.12.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.120.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.121.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.122.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.123.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.124.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.125.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.126.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.127.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.13.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.14.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.15.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.16.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.17.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.18.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.19.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.2.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w1.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w1.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w2.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w2.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w3.weight": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.20.w3.weight_scale": "consolidated-00146-of-00272.safetensors",
+ "layers.4.experts.21.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.21.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.21.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.21.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.21.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.21.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.22.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.23.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.24.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.25.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.26.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.27.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.28.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.29.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.3.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.30.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.31.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.32.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.33.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.34.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.35.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.36.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.37.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.38.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.39.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.4.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.40.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.41.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.42.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.43.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.44.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.45.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w2.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w2.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w3.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.46.w3.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.47.w1.weight": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.47.w1.weight_scale": "consolidated-00147-of-00272.safetensors",
+ "layers.4.experts.47.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.47.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.47.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.47.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.48.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.49.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.5.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.50.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.51.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.52.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.53.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.54.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.55.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.56.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.57.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.58.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.59.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.6.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.60.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.61.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.62.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.63.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.64.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.65.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.66.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.67.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.68.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.69.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.7.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.70.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w3.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.71.w3.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.72.w1.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.72.w1.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.72.w2.weight": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.72.w2.weight_scale": "consolidated-00148-of-00272.safetensors",
+ "layers.4.experts.72.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.72.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.73.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.74.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.75.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.76.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.77.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.78.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.79.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.8.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.80.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.81.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.82.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.83.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.84.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.85.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.86.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.87.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.88.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.89.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.9.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.90.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.91.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.92.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.93.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.94.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.95.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.96.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.97.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w1.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w1.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w2.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w2.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w3.weight": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.98.w3.weight_scale": "consolidated-00149-of-00272.safetensors",
+ "layers.4.experts.99.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.experts.99.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.4.experts.99.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.experts.99.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.4.experts.99.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.experts.99.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.4.ffn_norm.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.gate.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.4.shared_experts.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.kv_a_norm.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.q_a_norm.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wkv_a_with_mqa.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wkv_b.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wkv_b.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wo.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wo.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wq_a.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wq_b.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention.wq_b.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.attention_norm.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.0.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.1.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.10.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.100.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.101.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.102.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.103.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.104.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.105.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.106.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.107.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.108.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.109.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.11.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.110.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.111.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.112.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.113.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.114.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.115.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.116.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.117.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.118.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w1.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w1.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w2.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w2.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w3.weight": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.119.w3.weight_scale": "consolidated-00150-of-00272.safetensors",
+ "layers.40.experts.12.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.12.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.12.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.12.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.12.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.12.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.120.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.121.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.122.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.123.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.124.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.125.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.126.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.127.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.13.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.14.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.15.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.16.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.17.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.18.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.19.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.2.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.20.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.21.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.22.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.23.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.24.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.25.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.26.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.27.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.28.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.29.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w2.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w2.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w3.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.3.w3.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.30.w1.weight": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.30.w1.weight_scale": "consolidated-00151-of-00272.safetensors",
+ "layers.40.experts.30.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.30.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.30.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.30.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.31.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.32.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.33.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.34.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.35.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.36.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.37.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.38.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.39.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.4.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.40.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.41.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.42.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.43.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.44.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.45.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.46.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.47.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.48.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.49.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.5.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.50.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.51.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.52.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.53.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.54.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w3.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.55.w3.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.56.w1.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.56.w1.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.56.w2.weight": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.56.w2.weight_scale": "consolidated-00152-of-00272.safetensors",
+ "layers.40.experts.56.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.56.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.57.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.58.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.59.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.6.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.60.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.61.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.62.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.63.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.64.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.65.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.66.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.67.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.68.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.69.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.7.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.70.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.71.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.72.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.73.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.74.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.75.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.76.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.77.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.78.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.79.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.8.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.80.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w1.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w1.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w2.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w2.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w3.weight": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.81.w3.weight_scale": "consolidated-00153-of-00272.safetensors",
+ "layers.40.experts.82.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.82.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.82.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.82.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.82.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.82.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.83.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.84.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.85.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.86.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.87.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.88.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.89.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.9.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.90.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.91.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.92.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.93.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.94.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.95.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.96.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.97.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.98.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.experts.99.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.ffn_norm.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.gate.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.40.shared_experts.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.kv_a_norm.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.q_a_norm.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wkv_a_with_mqa.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wkv_b.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wkv_b.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wo.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wo.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wq_a.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wq_b.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention.wq_b.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.attention_norm.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.0.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.1.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.10.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.100.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.101.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w1.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w1.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w2.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w2.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w3.weight": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.102.w3.weight_scale": "consolidated-00154-of-00272.safetensors",
+ "layers.41.experts.103.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.103.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.103.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.103.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.103.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.103.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.104.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.105.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.106.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.107.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.108.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.109.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.11.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.110.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.111.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.112.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.113.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.114.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.115.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.116.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.117.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.118.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.119.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.12.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.120.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.121.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.122.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.123.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.124.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.125.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.126.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.127.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w2.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w2.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w3.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.13.w3.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.14.w1.weight": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.14.w1.weight_scale": "consolidated-00155-of-00272.safetensors",
+ "layers.41.experts.14.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.14.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.14.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.14.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.15.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.16.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.17.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.18.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.19.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.2.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.20.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.21.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.22.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.23.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.24.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.25.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.26.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.27.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.28.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.29.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.3.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.30.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.31.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.32.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.33.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.34.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.35.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.36.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.37.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.38.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w3.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.39.w3.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.4.w1.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.4.w1.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.4.w2.weight": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.4.w2.weight_scale": "consolidated-00156-of-00272.safetensors",
+ "layers.41.experts.4.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.4.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.40.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.41.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.42.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.43.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.44.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.45.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.46.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.47.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.48.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.49.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.5.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.50.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.51.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.52.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.53.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.54.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.55.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.56.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.57.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.58.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.59.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.6.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.60.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.61.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.62.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.63.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.64.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w1.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w1.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w2.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w2.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w3.weight": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.65.w3.weight_scale": "consolidated-00157-of-00272.safetensors",
+ "layers.41.experts.66.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.66.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.66.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.66.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.66.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.66.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.67.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.68.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.69.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.7.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.70.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.71.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.72.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.73.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.74.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.75.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.76.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.77.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.78.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.79.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.8.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.80.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.81.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.82.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.83.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.84.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.85.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.86.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.87.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.88.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.89.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.9.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w2.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w2.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w3.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.90.w3.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.91.w1.weight": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.91.w1.weight_scale": "consolidated-00158-of-00272.safetensors",
+ "layers.41.experts.91.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.91.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.91.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.91.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.92.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.93.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.94.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.95.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.96.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.97.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.98.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.experts.99.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.ffn_norm.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.gate.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.41.shared_experts.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.kv_a_norm.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.q_a_norm.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wkv_a_with_mqa.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wkv_b.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wkv_b.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wo.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wo.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wq_a.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wq_b.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention.wq_b.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.attention_norm.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.0.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.1.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.10.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.100.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.101.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.102.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.103.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.104.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.105.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.106.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.107.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.108.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.109.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.11.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.110.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w2.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w2.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w3.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.111.w3.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.112.w1.weight": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.112.w1.weight_scale": "consolidated-00159-of-00272.safetensors",
+ "layers.42.experts.112.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.112.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.112.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.112.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.113.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.114.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.115.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.116.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.117.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.118.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.119.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.12.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.120.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.121.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.122.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.123.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.124.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.125.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.126.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.127.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.13.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.14.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.15.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.16.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.17.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.18.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.19.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.2.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.20.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.21.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w3.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.22.w3.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.23.w1.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.23.w1.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.23.w2.weight": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.23.w2.weight_scale": "consolidated-00160-of-00272.safetensors",
+ "layers.42.experts.23.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.23.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.24.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.25.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.26.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.27.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.28.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.29.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.3.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.30.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.31.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.32.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.33.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.34.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.35.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.36.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.37.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.38.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.39.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.4.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.40.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.41.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.42.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.43.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.44.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.45.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.46.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.47.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.48.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w1.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w1.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w2.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w2.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w3.weight": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.49.w3.weight_scale": "consolidated-00161-of-00272.safetensors",
+ "layers.42.experts.5.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.5.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.5.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.5.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.5.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.5.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.50.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.51.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.52.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.53.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.54.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.55.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.56.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.57.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.58.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.59.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.6.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.60.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.61.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.62.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.63.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.64.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.65.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.66.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.67.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.68.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.69.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.7.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.70.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.71.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.72.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.73.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w2.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w2.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w3.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.74.w3.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.75.w1.weight": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.75.w1.weight_scale": "consolidated-00162-of-00272.safetensors",
+ "layers.42.experts.75.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.75.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.75.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.75.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.76.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.77.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.78.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.79.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.8.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.80.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.81.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.82.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.83.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.84.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.85.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.86.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.87.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.88.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.89.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.9.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.90.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.91.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.92.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.93.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.94.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.95.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.96.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.97.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.98.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.experts.99.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.ffn_norm.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.gate.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w1.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w1.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w2.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w2.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w3.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.42.shared_experts.w3.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.kv_a_norm.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.q_a_norm.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.wkv_a_with_mqa.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.wkv_b.weight": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.wkv_b.weight_scale": "consolidated-00163-of-00272.safetensors",
+ "layers.43.attention.wo.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.attention.wo.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.attention.wq_a.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.attention.wq_b.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.attention.wq_b.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.attention_norm.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.0.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.1.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.10.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.100.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.101.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.102.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.103.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.104.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.105.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.106.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.107.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.108.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.109.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.11.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.110.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.111.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.112.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.113.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.114.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.115.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.116.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.117.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.118.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.119.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.12.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w2.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w2.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w3.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.120.w3.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.121.w1.weight": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.121.w1.weight_scale": "consolidated-00164-of-00272.safetensors",
+ "layers.43.experts.121.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.121.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.121.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.121.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.122.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.123.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.124.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.125.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.126.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.127.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.13.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.14.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.15.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.16.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.17.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.18.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.19.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.2.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.20.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.21.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.22.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.23.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.24.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.25.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.26.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.27.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.28.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.29.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.3.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.30.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w3.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.31.w3.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.32.w1.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.32.w1.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.32.w2.weight": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.32.w2.weight_scale": "consolidated-00165-of-00272.safetensors",
+ "layers.43.experts.32.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.32.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.33.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.34.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.35.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.36.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.37.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.38.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.39.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.4.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.40.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.41.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.42.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.43.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.44.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.45.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.46.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.47.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.48.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.49.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.5.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.50.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.51.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.52.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.53.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.54.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.55.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.56.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.57.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w1.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w1.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w2.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w2.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w3.weight": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.58.w3.weight_scale": "consolidated-00166-of-00272.safetensors",
+ "layers.43.experts.59.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.59.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.59.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.59.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.59.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.59.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.6.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.60.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.61.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.62.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.63.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.64.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.65.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.66.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.67.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.68.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.69.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.7.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.70.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.71.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.72.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.73.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.74.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.75.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.76.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.77.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.78.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.79.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.8.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.80.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.81.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.82.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w2.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w2.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w3.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.83.w3.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.84.w1.weight": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.84.w1.weight_scale": "consolidated-00167-of-00272.safetensors",
+ "layers.43.experts.84.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.84.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.84.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.84.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.85.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.86.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.87.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.88.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.89.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.9.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.90.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.91.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.92.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.93.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.94.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.95.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.96.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.97.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.98.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.experts.99.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.ffn_norm.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.gate.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.43.shared_experts.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.kv_a_norm.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.q_a_norm.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wkv_a_with_mqa.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wkv_b.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wkv_b.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wo.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wo.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wq_a.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wq_b.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention.wq_b.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.attention_norm.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.0.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.1.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.10.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.100.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.101.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.102.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.103.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w2.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w2.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w3.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.104.w3.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.105.w1.weight": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.105.w1.weight_scale": "consolidated-00168-of-00272.safetensors",
+ "layers.44.experts.105.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.105.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.105.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.105.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.106.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.107.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.108.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.109.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.11.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.110.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.111.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.112.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.113.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.114.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.115.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.116.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.117.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.118.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.119.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.12.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.120.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.121.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.122.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.123.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.124.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.125.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.126.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.127.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.13.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.14.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w3.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.15.w3.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.16.w1.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.16.w1.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.16.w2.weight": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.16.w2.weight_scale": "consolidated-00169-of-00272.safetensors",
+ "layers.44.experts.16.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.16.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.17.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.18.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.19.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.2.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.20.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.21.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.22.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.23.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.24.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.25.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.26.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.27.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.28.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.29.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.3.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.30.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.31.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.32.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.33.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.34.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.35.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.36.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.37.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.38.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.39.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.4.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.40.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w1.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w1.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w2.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w2.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w3.weight": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.41.w3.weight_scale": "consolidated-00170-of-00272.safetensors",
+ "layers.44.experts.42.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.42.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.42.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.42.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.42.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.42.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.43.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.44.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.45.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.46.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.47.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.48.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.49.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.5.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.50.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.51.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.52.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.53.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.54.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.55.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.56.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.57.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.58.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.59.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.6.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.60.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.61.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.62.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.63.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.64.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.65.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.66.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w2.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w2.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w3.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.67.w3.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.68.w1.weight": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.68.w1.weight_scale": "consolidated-00171-of-00272.safetensors",
+ "layers.44.experts.68.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.68.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.68.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.68.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.69.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.7.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.70.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.71.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.72.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.73.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.74.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.75.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.76.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.77.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.78.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.79.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.8.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.80.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.81.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.82.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.83.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.84.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.85.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.86.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.87.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.88.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.89.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.9.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.90.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.91.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w3.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.92.w3.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.93.w1.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.93.w1.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.93.w2.weight": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.93.w2.weight_scale": "consolidated-00172-of-00272.safetensors",
+ "layers.44.experts.93.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.93.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.94.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.95.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.96.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.97.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.98.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.experts.99.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.ffn_norm.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.gate.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.44.shared_experts.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.kv_a_norm.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.q_a_norm.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wkv_a_with_mqa.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wkv_b.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wkv_b.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wo.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wo.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wq_a.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wq_b.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention.wq_b.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.attention_norm.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.0.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.1.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.10.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.100.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.101.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.102.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.103.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.104.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.105.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.106.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.107.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.108.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.109.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.11.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.110.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.111.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.112.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w3.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.113.w3.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.114.w1.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.114.w1.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.114.w2.weight": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.114.w2.weight_scale": "consolidated-00173-of-00272.safetensors",
+ "layers.45.experts.114.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.114.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.115.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.116.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.117.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.118.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.119.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.12.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.120.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.121.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.122.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.123.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.124.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.125.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.126.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.127.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.13.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.14.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.15.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.16.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.17.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.18.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.19.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.2.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.20.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.21.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.22.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.23.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.24.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w1.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w1.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w2.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w2.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w3.weight": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.25.w3.weight_scale": "consolidated-00174-of-00272.safetensors",
+ "layers.45.experts.26.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.26.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.26.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.26.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.26.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.26.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.27.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.28.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.29.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.3.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.30.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.31.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.32.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.33.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.34.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.35.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.36.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.37.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.38.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.39.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.4.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.40.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.41.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.42.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.43.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.44.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.45.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.46.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.47.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.48.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.49.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.5.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w2.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w2.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w3.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.50.w3.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.51.w1.weight": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.51.w1.weight_scale": "consolidated-00175-of-00272.safetensors",
+ "layers.45.experts.51.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.51.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.51.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.51.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.52.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.53.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.54.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.55.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.56.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.57.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.58.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.59.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.6.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.60.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.61.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.62.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.63.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.64.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.65.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.66.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.67.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.68.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.69.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.7.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.70.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.71.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.72.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.73.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.74.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.75.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w3.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.76.w3.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.77.w1.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.77.w1.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.77.w2.weight": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.77.w2.weight_scale": "consolidated-00176-of-00272.safetensors",
+ "layers.45.experts.77.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.77.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.78.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.79.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.8.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.80.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.81.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.82.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.83.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.84.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.85.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.86.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.87.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.88.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.89.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.9.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.90.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.91.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.92.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.93.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.94.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.95.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.96.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.97.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.98.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.experts.99.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.ffn_norm.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.gate.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w3.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.45.shared_experts.w3.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.kv_a_norm.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.q_a_norm.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wkv_a_with_mqa.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wkv_b.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wkv_b.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wo.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wo.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wq_a.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wq_b.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention.wq_b.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.attention_norm.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.experts.0.w1.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.experts.0.w1.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.experts.0.w2.weight": "consolidated-00177-of-00272.safetensors",
+ "layers.46.experts.0.w2.weight_scale": "consolidated-00177-of-00272.safetensors",
+ "layers.46.experts.0.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.0.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.1.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.10.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.100.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.101.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.102.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.103.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.104.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.105.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.106.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.107.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.108.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.109.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.11.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.110.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.111.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.112.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.113.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.114.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.115.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.116.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.117.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.118.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.119.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.12.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.120.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.121.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.122.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w1.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w1.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w2.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w2.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w3.weight": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.123.w3.weight_scale": "consolidated-00178-of-00272.safetensors",
+ "layers.46.experts.124.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.124.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.124.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.124.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.124.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.124.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.125.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.126.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.127.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.13.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.14.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.15.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.16.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.17.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.18.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.19.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.2.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.20.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.21.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.22.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.23.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.24.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.25.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.26.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.27.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.28.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.29.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.3.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.30.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.31.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.32.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.33.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w2.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w2.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w3.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.34.w3.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.35.w1.weight": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.35.w1.weight_scale": "consolidated-00179-of-00272.safetensors",
+ "layers.46.experts.35.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.35.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.35.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.35.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.36.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.37.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.38.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.39.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.4.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.40.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.41.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.42.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.43.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.44.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.45.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.46.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.47.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.48.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.49.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.5.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.50.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.51.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.52.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.53.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.54.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.55.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.56.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.57.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.58.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.59.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w3.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.6.w3.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.60.w1.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.60.w1.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.60.w2.weight": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.60.w2.weight_scale": "consolidated-00180-of-00272.safetensors",
+ "layers.46.experts.60.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.60.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.61.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.62.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.63.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.64.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.65.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.66.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.67.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.68.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.69.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.7.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.70.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.71.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.72.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.73.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.74.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.75.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.76.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.77.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.78.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.79.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.8.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.80.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.81.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.82.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.83.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.84.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.85.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w1.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w1.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w2.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w2.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w3.weight": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.86.w3.weight_scale": "consolidated-00181-of-00272.safetensors",
+ "layers.46.experts.87.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.87.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.87.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.87.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.87.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.87.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.88.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.89.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.9.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.90.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.91.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.92.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.93.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.94.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.95.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.96.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.97.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.98.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.experts.99.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.ffn_norm.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.gate.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.46.shared_experts.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.kv_a_norm.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.q_a_norm.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wkv_a_with_mqa.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wkv_b.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wkv_b.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wo.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wo.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wq_a.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wq_b.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention.wq_b.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.attention_norm.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.0.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.1.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.10.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.100.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.101.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.102.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.103.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.104.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.105.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.106.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w1.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w1.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w2.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w2.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w3.weight": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.107.w3.weight_scale": "consolidated-00182-of-00272.safetensors",
+ "layers.47.experts.108.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.108.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.108.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.108.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.108.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.108.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.109.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.11.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.110.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.111.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.112.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.113.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.114.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.115.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.116.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.117.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.118.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.119.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.12.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.120.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.121.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.122.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.123.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.124.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.125.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.126.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.127.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.13.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.14.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.15.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.16.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.17.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w2.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w2.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w3.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.18.w3.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.19.w1.weight": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.19.w1.weight_scale": "consolidated-00183-of-00272.safetensors",
+ "layers.47.experts.19.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.19.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.19.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.19.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.2.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.20.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.21.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.22.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.23.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.24.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.25.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.26.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.27.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.28.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.29.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.3.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.30.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.31.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.32.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.33.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.34.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.35.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.36.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.37.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.38.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.39.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.4.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.40.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.41.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.42.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w3.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.43.w3.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.44.w1.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.44.w1.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.44.w2.weight": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.44.w2.weight_scale": "consolidated-00184-of-00272.safetensors",
+ "layers.47.experts.44.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.44.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.45.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.46.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.47.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.48.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.49.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.5.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.50.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.51.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.52.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.53.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.54.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.55.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.56.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.57.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.58.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.59.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.6.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.60.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.61.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.62.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.63.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.64.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.65.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.66.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.67.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.68.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.69.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w1.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w1.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w2.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w2.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w3.weight": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.7.w3.weight_scale": "consolidated-00185-of-00272.safetensors",
+ "layers.47.experts.70.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.70.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.70.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.70.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.70.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.70.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.71.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.72.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.73.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.74.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.75.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.76.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.77.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.78.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.79.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.8.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.80.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.81.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.82.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.83.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.84.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.85.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.86.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.87.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.88.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.89.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.9.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.90.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.91.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.92.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.93.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.94.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w2.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w2.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w3.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.95.w3.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.96.w1.weight": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.96.w1.weight_scale": "consolidated-00186-of-00272.safetensors",
+ "layers.47.experts.96.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.96.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.96.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.96.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.97.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.98.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.experts.99.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.ffn_norm.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.gate.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.47.shared_experts.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.kv_a_norm.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.q_a_norm.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wkv_a_with_mqa.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wkv_b.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wkv_b.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wo.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wo.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wq_a.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wq_b.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention.wq_b.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.attention_norm.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.0.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.1.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.10.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.100.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.101.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.102.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.103.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.104.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.105.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.106.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.107.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.108.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.109.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.11.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.110.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.111.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.112.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.113.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.114.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.115.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w2.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w2.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w3.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.116.w3.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.117.w1.weight": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.117.w1.weight_scale": "consolidated-00187-of-00272.safetensors",
+ "layers.48.experts.117.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.117.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.117.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.117.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.118.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.119.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.12.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.120.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.121.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.122.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.123.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.124.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.125.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.126.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.127.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.13.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.14.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.15.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.16.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.17.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.18.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.19.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.2.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.20.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.21.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.22.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.23.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.24.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.25.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.26.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w3.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.27.w3.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.28.w1.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.28.w1.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.28.w2.weight": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.28.w2.weight_scale": "consolidated-00188-of-00272.safetensors",
+ "layers.48.experts.28.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.28.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.29.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.3.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.30.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.31.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.32.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.33.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.34.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.35.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.36.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.37.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.38.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.39.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.4.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.40.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.41.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.42.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.43.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.44.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.45.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.46.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.47.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.48.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.49.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.5.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.50.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.51.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.52.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w1.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w1.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w2.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w2.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w3.weight": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.53.w3.weight_scale": "consolidated-00189-of-00272.safetensors",
+ "layers.48.experts.54.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.54.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.54.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.54.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.54.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.54.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.55.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.56.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.57.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.58.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.59.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.6.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.60.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.61.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.62.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.63.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.64.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.65.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.66.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.67.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.68.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.69.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.7.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.70.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.71.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.72.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.73.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.74.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.75.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.76.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.77.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.78.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w2.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w2.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w3.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.79.w3.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.8.w1.weight": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.8.w1.weight_scale": "consolidated-00190-of-00272.safetensors",
+ "layers.48.experts.8.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.8.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.8.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.8.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.80.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.81.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.82.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.83.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.84.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.85.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.86.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.87.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.88.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.89.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.9.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.90.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.91.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.92.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.93.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.94.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.95.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.96.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.97.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.98.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.experts.99.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.ffn_norm.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.gate.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.48.shared_experts.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.kv_a_norm.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.q_a_norm.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wkv_a_with_mqa.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wkv_b.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wkv_b.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wo.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wo.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wq_a.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wq_b.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention.wq_b.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.attention_norm.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.0.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.1.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w2.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w2.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w3.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.10.w3.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.100.w1.weight": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.100.w1.weight_scale": "consolidated-00191-of-00272.safetensors",
+ "layers.49.experts.100.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.100.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.100.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.100.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.101.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.102.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.103.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.104.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.105.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.106.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.107.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.108.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.109.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.11.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.110.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.111.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.112.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.113.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.114.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.115.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.116.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.117.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.118.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.119.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.12.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.120.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.121.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.122.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.123.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.124.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w3.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.125.w3.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.126.w1.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.126.w1.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.126.w2.weight": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.126.w2.weight_scale": "consolidated-00192-of-00272.safetensors",
+ "layers.49.experts.126.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.126.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.127.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.13.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.14.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.15.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.16.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.17.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.18.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.19.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.2.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.20.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.21.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.22.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.23.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.24.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.25.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.26.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.27.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.28.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.29.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.3.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.30.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.31.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.32.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.33.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.34.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.35.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.36.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w1.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w1.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w2.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w2.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w3.weight": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.37.w3.weight_scale": "consolidated-00193-of-00272.safetensors",
+ "layers.49.experts.38.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.38.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.38.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.38.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.38.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.38.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.39.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.4.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.40.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.41.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.42.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.43.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.44.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.45.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.46.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.47.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.48.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.49.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.5.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.50.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.51.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.52.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.53.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.54.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.55.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.56.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.57.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.58.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.59.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.6.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.60.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.61.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w2.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w2.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w3.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.62.w3.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.63.w1.weight": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.63.w1.weight_scale": "consolidated-00194-of-00272.safetensors",
+ "layers.49.experts.63.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.63.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.63.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.63.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.64.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.65.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.66.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.67.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.68.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.69.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.7.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.70.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.71.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.72.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.73.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.74.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.75.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.76.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.77.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.78.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.79.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.8.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.80.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.81.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.82.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.83.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.84.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.85.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.86.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.87.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w3.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.88.w3.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.89.w1.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.89.w1.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.89.w2.weight": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.89.w2.weight_scale": "consolidated-00195-of-00272.safetensors",
+ "layers.49.experts.89.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.89.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.9.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.90.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.91.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.92.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.93.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.94.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.95.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.96.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.97.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.98.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.experts.99.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.ffn_norm.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.gate.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.49.shared_experts.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.kv_a_norm.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.q_a_norm.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wkv_a_with_mqa.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wkv_b.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wkv_b.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wo.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wo.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wq_a.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wq_b.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention.wq_b.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.attention_norm.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.0.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.1.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.10.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.100.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.101.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.102.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.103.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.104.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.105.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.106.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.107.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.108.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w3.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.109.w3.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.11.w1.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.11.w1.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.11.w2.weight": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.11.w2.weight_scale": "consolidated-00196-of-00272.safetensors",
+ "layers.5.experts.11.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.11.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.110.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.111.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.112.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.113.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.114.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.115.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.116.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.117.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.118.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.119.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.12.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.120.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.121.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.122.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.123.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.124.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.125.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.126.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.127.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.13.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.14.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.15.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.16.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.17.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.18.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.19.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.2.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w1.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w1.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w2.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w2.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w3.weight": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.20.w3.weight_scale": "consolidated-00197-of-00272.safetensors",
+ "layers.5.experts.21.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.21.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.21.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.21.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.21.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.21.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.22.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.23.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.24.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.25.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.26.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.27.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.28.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.29.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.3.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.30.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.31.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.32.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.33.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.34.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.35.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.36.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.37.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.38.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.39.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.4.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.40.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.41.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.42.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.43.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.44.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.45.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w2.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w2.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w3.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.46.w3.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.47.w1.weight": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.47.w1.weight_scale": "consolidated-00198-of-00272.safetensors",
+ "layers.5.experts.47.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.47.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.47.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.47.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.48.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.49.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.5.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.50.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.51.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.52.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.53.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.54.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.55.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.56.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.57.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.58.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.59.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.6.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.60.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.61.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.62.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.63.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.64.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.65.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.66.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.67.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.68.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.69.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.7.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.70.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w3.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.71.w3.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.72.w1.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.72.w1.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.72.w2.weight": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.72.w2.weight_scale": "consolidated-00199-of-00272.safetensors",
+ "layers.5.experts.72.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.72.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.73.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.74.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.75.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.76.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.77.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.78.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.79.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.8.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.80.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.81.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.82.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.83.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.84.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.85.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.86.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.87.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.88.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.89.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.9.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.90.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.91.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.92.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.93.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.94.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.95.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.96.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.97.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w1.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w1.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w2.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w2.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w3.weight": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.98.w3.weight_scale": "consolidated-00200-of-00272.safetensors",
+ "layers.5.experts.99.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.experts.99.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.5.experts.99.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.experts.99.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.5.experts.99.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.experts.99.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.5.ffn_norm.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.gate.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.5.shared_experts.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.kv_a_norm.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.q_a_norm.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wkv_a_with_mqa.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wkv_b.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wkv_b.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wo.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wo.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wq_a.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wq_b.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention.wq_b.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.attention_norm.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.0.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.1.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.10.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.100.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.101.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.102.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.103.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.104.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.105.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.106.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.107.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.108.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.109.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.11.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.110.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.111.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.112.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.113.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.114.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.115.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.116.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.117.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.118.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w1.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w1.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w2.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w2.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w3.weight": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.119.w3.weight_scale": "consolidated-00201-of-00272.safetensors",
+ "layers.50.experts.12.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.12.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.12.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.12.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.12.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.12.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.120.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.121.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.122.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.123.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.124.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.125.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.126.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.127.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.13.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.14.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.15.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.16.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.17.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.18.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.19.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.2.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.20.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.21.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.22.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.23.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.24.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.25.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.26.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.27.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.28.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.29.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w2.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w2.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w3.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.3.w3.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.30.w1.weight": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.30.w1.weight_scale": "consolidated-00202-of-00272.safetensors",
+ "layers.50.experts.30.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.30.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.30.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.30.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.31.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.32.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.33.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.34.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.35.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.36.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.37.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.38.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.39.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.4.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.40.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.41.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.42.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.43.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.44.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.45.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.46.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.47.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.48.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.49.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.5.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.50.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.51.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.52.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.53.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.54.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w3.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.55.w3.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.56.w1.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.56.w1.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.56.w2.weight": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.56.w2.weight_scale": "consolidated-00203-of-00272.safetensors",
+ "layers.50.experts.56.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.56.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.57.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.58.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.59.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.6.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.60.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.61.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.62.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.63.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.64.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.65.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.66.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.67.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.68.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.69.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.7.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.70.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.71.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.72.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.73.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.74.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.75.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.76.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.77.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.78.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.79.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.8.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.80.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w1.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w1.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w2.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w2.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w3.weight": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.81.w3.weight_scale": "consolidated-00204-of-00272.safetensors",
+ "layers.50.experts.82.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.82.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.82.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.82.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.82.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.82.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.83.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.84.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.85.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.86.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.87.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.88.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.89.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.9.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.90.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.91.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.92.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.93.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.94.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.95.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.96.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.97.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.98.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.experts.99.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.ffn_norm.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.gate.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.50.shared_experts.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.kv_a_norm.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.q_a_norm.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wkv_a_with_mqa.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wkv_b.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wkv_b.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wo.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wo.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wq_a.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wq_b.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention.wq_b.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.attention_norm.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.0.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.1.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.10.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.100.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.101.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w1.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w1.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w2.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w2.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w3.weight": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.102.w3.weight_scale": "consolidated-00205-of-00272.safetensors",
+ "layers.51.experts.103.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.103.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.103.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.103.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.103.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.103.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.104.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.105.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.106.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.107.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.108.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.109.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.11.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.110.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.111.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.112.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.113.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.114.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.115.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.116.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.117.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.118.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.119.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.12.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.120.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.121.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.122.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.123.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.124.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.125.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.126.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.127.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w2.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w2.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w3.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.13.w3.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.14.w1.weight": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.14.w1.weight_scale": "consolidated-00206-of-00272.safetensors",
+ "layers.51.experts.14.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.14.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.14.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.14.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.15.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.16.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.17.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.18.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.19.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.2.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.20.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.21.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.22.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.23.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.24.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.25.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.26.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.27.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.28.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.29.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.3.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.30.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.31.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.32.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.33.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.34.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.35.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.36.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.37.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.38.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w3.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.39.w3.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.4.w1.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.4.w1.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.4.w2.weight": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.4.w2.weight_scale": "consolidated-00207-of-00272.safetensors",
+ "layers.51.experts.4.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.4.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.40.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.41.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.42.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.43.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.44.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.45.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.46.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.47.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.48.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.49.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.5.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.50.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.51.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.52.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.53.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.54.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.55.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.56.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.57.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.58.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.59.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.6.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.60.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.61.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.62.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.63.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.64.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w1.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w1.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w2.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w2.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w3.weight": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.65.w3.weight_scale": "consolidated-00208-of-00272.safetensors",
+ "layers.51.experts.66.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.66.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.66.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.66.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.66.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.66.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.67.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.68.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.69.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.7.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.70.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.71.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.72.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.73.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.74.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.75.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.76.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.77.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.78.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.79.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.8.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.80.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.81.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.82.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.83.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.84.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.85.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.86.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.87.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.88.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.89.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.9.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w2.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w2.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w3.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.90.w3.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.91.w1.weight": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.91.w1.weight_scale": "consolidated-00209-of-00272.safetensors",
+ "layers.51.experts.91.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.91.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.91.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.91.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.92.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.93.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.94.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.95.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.96.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.97.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.98.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.experts.99.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.ffn_norm.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.gate.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.51.shared_experts.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.kv_a_norm.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.q_a_norm.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wkv_a_with_mqa.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wkv_b.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wkv_b.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wo.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wo.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wq_a.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wq_b.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention.wq_b.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.attention_norm.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.0.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.1.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.10.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.100.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.101.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.102.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.103.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.104.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.105.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.106.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.107.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.108.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.109.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.11.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.110.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w2.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w2.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w3.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.111.w3.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.112.w1.weight": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.112.w1.weight_scale": "consolidated-00210-of-00272.safetensors",
+ "layers.52.experts.112.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.112.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.112.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.112.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.113.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.114.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.115.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.116.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.117.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.118.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.119.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.12.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.120.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.121.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.122.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.123.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.124.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.125.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.126.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.127.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.13.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.14.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.15.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.16.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.17.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.18.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.19.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.2.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.20.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.21.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w3.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.22.w3.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.23.w1.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.23.w1.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.23.w2.weight": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.23.w2.weight_scale": "consolidated-00211-of-00272.safetensors",
+ "layers.52.experts.23.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.23.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.24.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.25.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.26.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.27.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.28.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.29.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.3.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.30.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.31.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.32.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.33.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.34.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.35.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.36.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.37.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.38.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.39.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.4.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.40.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.41.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.42.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.43.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.44.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.45.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.46.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.47.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.48.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w1.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w1.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w2.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w2.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w3.weight": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.49.w3.weight_scale": "consolidated-00212-of-00272.safetensors",
+ "layers.52.experts.5.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.5.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.5.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.5.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.5.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.5.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.50.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.51.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.52.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.53.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.54.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.55.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.56.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.57.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.58.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.59.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.6.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.60.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.61.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.62.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.63.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.64.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.65.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.66.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.67.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.68.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.69.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.7.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.70.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.71.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.72.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.73.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w2.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w2.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w3.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.74.w3.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.75.w1.weight": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.75.w1.weight_scale": "consolidated-00213-of-00272.safetensors",
+ "layers.52.experts.75.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.75.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.75.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.75.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.76.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.77.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.78.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.79.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.8.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.80.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.81.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.82.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.83.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.84.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.85.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.86.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.87.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.88.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.89.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.9.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.90.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.91.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.92.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.93.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.94.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.95.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.96.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.97.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.98.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.experts.99.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.ffn_norm.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.gate.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w1.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w1.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w2.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w2.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w3.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.52.shared_experts.w3.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.kv_a_norm.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.q_a_norm.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.wkv_a_with_mqa.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.wkv_b.weight": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.wkv_b.weight_scale": "consolidated-00214-of-00272.safetensors",
+ "layers.53.attention.wo.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.attention.wo.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.attention.wq_a.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.attention.wq_b.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.attention.wq_b.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.attention_norm.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.0.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.1.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.10.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.100.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.101.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.102.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.103.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.104.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.105.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.106.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.107.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.108.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.109.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.11.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.110.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.111.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.112.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.113.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.114.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.115.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.116.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.117.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.118.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.119.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.12.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w2.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w2.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w3.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.120.w3.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.121.w1.weight": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.121.w1.weight_scale": "consolidated-00215-of-00272.safetensors",
+ "layers.53.experts.121.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.121.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.121.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.121.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.122.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.123.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.124.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.125.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.126.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.127.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.13.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.14.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.15.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.16.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.17.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.18.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.19.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.2.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.20.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.21.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.22.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.23.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.24.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.25.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.26.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.27.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.28.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.29.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.3.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.30.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w3.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.31.w3.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.32.w1.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.32.w1.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.32.w2.weight": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.32.w2.weight_scale": "consolidated-00216-of-00272.safetensors",
+ "layers.53.experts.32.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.32.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.33.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.34.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.35.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.36.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.37.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.38.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.39.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.4.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.40.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.41.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.42.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.43.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.44.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.45.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.46.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.47.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.48.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.49.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.5.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.50.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.51.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.52.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.53.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.54.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.55.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.56.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.57.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w1.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w1.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w2.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w2.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w3.weight": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.58.w3.weight_scale": "consolidated-00217-of-00272.safetensors",
+ "layers.53.experts.59.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.59.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.59.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.59.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.59.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.59.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.6.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.60.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.61.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.62.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.63.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.64.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.65.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.66.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.67.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.68.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.69.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.7.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.70.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.71.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.72.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.73.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.74.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.75.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.76.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.77.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.78.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.79.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.8.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.80.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.81.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.82.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w2.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w2.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w3.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.83.w3.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.84.w1.weight": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.84.w1.weight_scale": "consolidated-00218-of-00272.safetensors",
+ "layers.53.experts.84.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.84.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.84.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.84.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.85.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.86.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.87.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.88.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.89.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.9.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.90.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.91.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.92.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.93.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.94.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.95.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.96.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.97.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.98.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.experts.99.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.ffn_norm.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.gate.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.53.shared_experts.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.kv_a_norm.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.q_a_norm.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wkv_a_with_mqa.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wkv_b.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wkv_b.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wo.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wo.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wq_a.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wq_b.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention.wq_b.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.attention_norm.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.0.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.1.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.10.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.100.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.101.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.102.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.103.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w2.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w2.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w3.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.104.w3.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.105.w1.weight": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.105.w1.weight_scale": "consolidated-00219-of-00272.safetensors",
+ "layers.54.experts.105.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.105.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.105.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.105.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.106.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.107.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.108.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.109.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.11.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.110.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.111.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.112.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.113.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.114.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.115.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.116.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.117.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.118.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.119.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.12.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.120.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.121.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.122.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.123.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.124.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.125.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.126.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.127.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.13.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.14.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w3.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.15.w3.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.16.w1.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.16.w1.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.16.w2.weight": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.16.w2.weight_scale": "consolidated-00220-of-00272.safetensors",
+ "layers.54.experts.16.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.16.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.17.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.18.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.19.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.2.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.20.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.21.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.22.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.23.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.24.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.25.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.26.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.27.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.28.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.29.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.3.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.30.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.31.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.32.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.33.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.34.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.35.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.36.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.37.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.38.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.39.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.4.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.40.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w1.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w1.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w2.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w2.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w3.weight": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.41.w3.weight_scale": "consolidated-00221-of-00272.safetensors",
+ "layers.54.experts.42.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.42.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.42.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.42.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.42.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.42.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.43.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.44.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.45.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.46.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.47.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.48.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.49.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.5.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.50.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.51.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.52.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.53.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.54.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.55.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.56.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.57.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.58.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.59.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.6.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.60.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.61.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.62.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.63.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.64.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.65.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.66.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w2.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w2.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w3.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.67.w3.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.68.w1.weight": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.68.w1.weight_scale": "consolidated-00222-of-00272.safetensors",
+ "layers.54.experts.68.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.68.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.68.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.68.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.69.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.7.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.70.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.71.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.72.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.73.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.74.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.75.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.76.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.77.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.78.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.79.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.8.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.80.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.81.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.82.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.83.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.84.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.85.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.86.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.87.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.88.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.89.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.9.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.90.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.91.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w3.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.92.w3.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.93.w1.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.93.w1.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.93.w2.weight": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.93.w2.weight_scale": "consolidated-00223-of-00272.safetensors",
+ "layers.54.experts.93.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.93.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.94.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.95.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.96.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.97.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.98.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.experts.99.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.ffn_norm.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.gate.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.54.shared_experts.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.kv_a_norm.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.q_a_norm.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wkv_a_with_mqa.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wkv_b.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wkv_b.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wo.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wo.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wq_a.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wq_b.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention.wq_b.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.attention_norm.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.0.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.1.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.10.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.100.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.101.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.102.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.103.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.104.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.105.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.106.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.107.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.108.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.109.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.11.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.110.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.111.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.112.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w3.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.113.w3.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.114.w1.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.114.w1.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.114.w2.weight": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.114.w2.weight_scale": "consolidated-00224-of-00272.safetensors",
+ "layers.55.experts.114.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.114.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.115.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.116.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.117.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.118.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.119.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.12.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.120.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.121.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.122.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.123.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.124.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.125.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.126.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.127.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.13.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.14.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.15.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.16.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.17.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.18.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.19.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.2.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.20.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.21.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.22.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.23.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.24.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w1.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w1.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w2.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w2.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w3.weight": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.25.w3.weight_scale": "consolidated-00225-of-00272.safetensors",
+ "layers.55.experts.26.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.26.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.26.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.26.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.26.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.26.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.27.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.28.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.29.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.3.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.30.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.31.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.32.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.33.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.34.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.35.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.36.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.37.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.38.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.39.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.4.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.40.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.41.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.42.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.43.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.44.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.45.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.46.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.47.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.48.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.49.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.5.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w2.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w2.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w3.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.50.w3.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.51.w1.weight": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.51.w1.weight_scale": "consolidated-00226-of-00272.safetensors",
+ "layers.55.experts.51.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.51.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.51.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.51.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.52.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.53.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.54.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.55.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.56.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.57.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.58.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.59.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.6.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.60.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.61.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.62.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.63.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.64.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.65.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.66.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.67.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.68.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.69.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.7.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.70.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.71.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.72.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.73.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.74.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.75.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w3.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.76.w3.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.77.w1.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.77.w1.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.77.w2.weight": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.77.w2.weight_scale": "consolidated-00227-of-00272.safetensors",
+ "layers.55.experts.77.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.77.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.78.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.79.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.8.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.80.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.81.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.82.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.83.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.84.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.85.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.86.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.87.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.88.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.89.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.9.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.90.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.91.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.92.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.93.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.94.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.95.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.96.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.97.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.98.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.experts.99.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.ffn_norm.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.gate.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w3.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.55.shared_experts.w3.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.kv_a_norm.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.q_a_norm.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wkv_a_with_mqa.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wkv_b.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wkv_b.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wo.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wo.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wq_a.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wq_b.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention.wq_b.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.attention_norm.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.experts.0.w1.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.experts.0.w1.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.experts.0.w2.weight": "consolidated-00228-of-00272.safetensors",
+ "layers.56.experts.0.w2.weight_scale": "consolidated-00228-of-00272.safetensors",
+ "layers.56.experts.0.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.0.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.1.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.10.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.100.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.101.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.102.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.103.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.104.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.105.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.106.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.107.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.108.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.109.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.11.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.110.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.111.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.112.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.113.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.114.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.115.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.116.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.117.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.118.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.119.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.12.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.120.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.121.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.122.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w1.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w1.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w2.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w2.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w3.weight": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.123.w3.weight_scale": "consolidated-00229-of-00272.safetensors",
+ "layers.56.experts.124.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.124.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.124.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.124.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.124.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.124.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.125.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.126.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.127.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.13.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.14.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.15.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.16.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.17.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.18.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.19.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.2.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.20.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.21.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.22.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.23.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.24.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.25.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.26.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.27.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.28.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.29.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.3.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.30.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.31.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.32.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.33.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w2.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w2.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w3.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.34.w3.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.35.w1.weight": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.35.w1.weight_scale": "consolidated-00230-of-00272.safetensors",
+ "layers.56.experts.35.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.35.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.35.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.35.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.36.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.37.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.38.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.39.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.4.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.40.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.41.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.42.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.43.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.44.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.45.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.46.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.47.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.48.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.49.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.5.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.50.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.51.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.52.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.53.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.54.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.55.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.56.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.57.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.58.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.59.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w3.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.6.w3.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.60.w1.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.60.w1.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.60.w2.weight": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.60.w2.weight_scale": "consolidated-00231-of-00272.safetensors",
+ "layers.56.experts.60.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.60.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.61.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.62.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.63.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.64.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.65.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.66.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.67.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.68.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.69.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.7.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.70.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.71.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.72.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.73.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.74.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.75.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.76.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.77.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.78.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.79.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.8.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.80.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.81.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.82.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.83.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.84.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.85.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w1.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w1.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w2.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w2.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w3.weight": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.86.w3.weight_scale": "consolidated-00232-of-00272.safetensors",
+ "layers.56.experts.87.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.87.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.87.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.87.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.87.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.87.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.88.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.89.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.9.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.90.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.91.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.92.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.93.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.94.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.95.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.96.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.97.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.98.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.experts.99.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.ffn_norm.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.gate.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.56.shared_experts.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.kv_a_norm.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.q_a_norm.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wkv_a_with_mqa.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wkv_b.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wkv_b.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wo.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wo.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wq_a.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wq_b.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention.wq_b.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.attention_norm.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.0.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.1.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.10.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.100.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.101.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.102.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.103.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.104.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.105.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.106.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w1.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w1.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w2.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w2.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w3.weight": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.107.w3.weight_scale": "consolidated-00233-of-00272.safetensors",
+ "layers.57.experts.108.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.108.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.108.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.108.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.108.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.108.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.109.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.11.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.110.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.111.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.112.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.113.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.114.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.115.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.116.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.117.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.118.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.119.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.12.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.120.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.121.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.122.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.123.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.124.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.125.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.126.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.127.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.13.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.14.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.15.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.16.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.17.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w2.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w2.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w3.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.18.w3.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.19.w1.weight": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.19.w1.weight_scale": "consolidated-00234-of-00272.safetensors",
+ "layers.57.experts.19.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.19.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.19.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.19.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.2.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.20.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.21.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.22.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.23.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.24.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.25.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.26.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.27.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.28.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.29.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.3.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.30.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.31.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.32.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.33.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.34.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.35.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.36.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.37.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.38.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.39.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.4.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.40.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.41.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.42.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w3.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.43.w3.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.44.w1.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.44.w1.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.44.w2.weight": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.44.w2.weight_scale": "consolidated-00235-of-00272.safetensors",
+ "layers.57.experts.44.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.44.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.45.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.46.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.47.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.48.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.49.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.5.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.50.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.51.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.52.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.53.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.54.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.55.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.56.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.57.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.58.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.59.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.6.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.60.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.61.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.62.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.63.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.64.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.65.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.66.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.67.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.68.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.69.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w1.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w1.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w2.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w2.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w3.weight": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.7.w3.weight_scale": "consolidated-00236-of-00272.safetensors",
+ "layers.57.experts.70.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.70.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.70.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.70.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.70.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.70.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.71.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.72.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.73.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.74.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.75.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.76.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.77.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.78.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.79.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.8.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.80.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.81.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.82.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.83.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.84.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.85.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.86.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.87.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.88.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.89.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.9.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.90.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.91.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.92.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.93.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.94.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w2.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w2.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w3.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.95.w3.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.96.w1.weight": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.96.w1.weight_scale": "consolidated-00237-of-00272.safetensors",
+ "layers.57.experts.96.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.96.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.96.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.96.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.97.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.98.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.experts.99.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.ffn_norm.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.gate.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.57.shared_experts.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.kv_a_norm.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.q_a_norm.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wkv_a_with_mqa.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wkv_b.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wkv_b.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wo.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wo.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wq_a.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wq_b.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention.wq_b.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.attention_norm.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.0.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.1.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.10.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.100.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.101.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.102.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.103.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.104.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.105.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.106.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.107.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.108.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.109.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.11.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.110.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.111.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.112.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.113.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.114.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.115.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w2.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w2.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w3.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.116.w3.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.117.w1.weight": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.117.w1.weight_scale": "consolidated-00238-of-00272.safetensors",
+ "layers.58.experts.117.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.117.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.117.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.117.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.118.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.119.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.12.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.120.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.121.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.122.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.123.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.124.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.125.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.126.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.127.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.13.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.14.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.15.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.16.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.17.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.18.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.19.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.2.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.20.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.21.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.22.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.23.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.24.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.25.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.26.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w3.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.27.w3.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.28.w1.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.28.w1.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.28.w2.weight": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.28.w2.weight_scale": "consolidated-00239-of-00272.safetensors",
+ "layers.58.experts.28.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.28.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.29.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.3.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.30.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.31.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.32.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.33.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.34.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.35.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.36.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.37.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.38.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.39.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.4.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.40.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.41.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.42.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.43.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.44.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.45.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.46.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.47.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.48.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.49.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.5.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.50.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.51.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.52.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w1.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w1.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w2.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w2.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w3.weight": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.53.w3.weight_scale": "consolidated-00240-of-00272.safetensors",
+ "layers.58.experts.54.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.54.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.54.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.54.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.54.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.54.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.55.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.56.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.57.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.58.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.59.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.6.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.60.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.61.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.62.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.63.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.64.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.65.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.66.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.67.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.68.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.69.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.7.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.70.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.71.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.72.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.73.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.74.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.75.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.76.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.77.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.78.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w2.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w2.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w3.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.79.w3.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.8.w1.weight": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.8.w1.weight_scale": "consolidated-00241-of-00272.safetensors",
+ "layers.58.experts.8.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.8.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.8.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.8.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.80.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.81.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.82.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.83.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.84.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.85.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.86.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.87.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.88.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.89.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.9.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.90.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.91.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.92.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.93.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.94.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.95.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.96.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.97.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.98.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.experts.99.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.ffn_norm.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.gate.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.58.shared_experts.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.kv_a_norm.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.q_a_norm.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wkv_a_with_mqa.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wkv_b.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wkv_b.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wo.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wo.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wq_a.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wq_b.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention.wq_b.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.attention_norm.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.0.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.1.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w2.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w2.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w3.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.10.w3.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.100.w1.weight": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.100.w1.weight_scale": "consolidated-00242-of-00272.safetensors",
+ "layers.59.experts.100.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.100.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.100.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.100.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.101.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.102.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.103.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.104.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.105.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.106.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.107.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.108.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.109.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.11.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.110.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.111.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.112.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.113.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.114.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.115.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.116.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.117.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.118.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.119.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.12.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.120.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.121.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.122.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.123.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.124.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w3.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.125.w3.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.126.w1.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.126.w1.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.126.w2.weight": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.126.w2.weight_scale": "consolidated-00243-of-00272.safetensors",
+ "layers.59.experts.126.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.126.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.127.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.13.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.14.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.15.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.16.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.17.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.18.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.19.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.2.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.20.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.21.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.22.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.23.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.24.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.25.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.26.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.27.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.28.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.29.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.3.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.30.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.31.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.32.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.33.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.34.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.35.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.36.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w1.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w1.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w2.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w2.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w3.weight": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.37.w3.weight_scale": "consolidated-00244-of-00272.safetensors",
+ "layers.59.experts.38.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.38.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.38.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.38.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.38.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.38.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.39.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.4.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.40.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.41.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.42.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.43.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.44.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.45.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.46.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.47.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.48.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.49.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.5.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.50.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.51.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.52.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.53.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.54.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.55.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.56.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.57.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.58.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.59.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.6.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.60.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.61.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w2.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w2.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w3.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.62.w3.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.63.w1.weight": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.63.w1.weight_scale": "consolidated-00245-of-00272.safetensors",
+ "layers.59.experts.63.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.63.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.63.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.63.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.64.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.65.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.66.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.67.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.68.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.69.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.7.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.70.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.71.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.72.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.73.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.74.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.75.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.76.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.77.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.78.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.79.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.8.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.80.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.81.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.82.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.83.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.84.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.85.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.86.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.87.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w3.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.88.w3.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.89.w1.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.89.w1.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.89.w2.weight": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.89.w2.weight_scale": "consolidated-00246-of-00272.safetensors",
+ "layers.59.experts.89.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.89.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.9.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.90.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.91.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.92.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.93.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.94.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.95.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.96.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.97.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.98.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.experts.99.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.ffn_norm.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.gate.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.59.shared_experts.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.kv_a_norm.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.q_a_norm.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wkv_a_with_mqa.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wkv_b.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wkv_b.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wo.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wo.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wq_a.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wq_b.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention.wq_b.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.attention_norm.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.0.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.1.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.10.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.100.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.101.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.102.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.103.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.104.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.105.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.106.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.107.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.108.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w3.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.109.w3.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.11.w1.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.11.w1.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.11.w2.weight": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.11.w2.weight_scale": "consolidated-00247-of-00272.safetensors",
+ "layers.6.experts.11.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.11.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.110.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.111.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.112.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.113.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.114.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.115.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.116.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.117.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.118.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.119.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.12.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.120.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.121.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.122.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.123.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.124.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.125.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.126.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.127.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.13.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.14.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.15.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.16.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.17.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.18.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.19.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.2.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w1.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w1.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w2.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w2.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w3.weight": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.20.w3.weight_scale": "consolidated-00248-of-00272.safetensors",
+ "layers.6.experts.21.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.21.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.21.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.21.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.21.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.21.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.22.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.23.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.24.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.25.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.26.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.27.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.28.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.29.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.3.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.30.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.31.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.32.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.33.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.34.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.35.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.36.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.37.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.38.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.39.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.4.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.40.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.41.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.42.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.43.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.44.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.45.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w2.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w2.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w3.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.46.w3.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.47.w1.weight": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.47.w1.weight_scale": "consolidated-00249-of-00272.safetensors",
+ "layers.6.experts.47.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.47.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.47.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.47.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.48.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.49.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.5.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.50.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.51.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.52.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.53.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.54.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.55.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.56.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.57.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.58.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.59.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.6.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.60.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.61.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.62.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.63.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.64.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.65.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.66.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.67.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.68.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.69.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.7.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.70.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w3.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.71.w3.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.72.w1.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.72.w1.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.72.w2.weight": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.72.w2.weight_scale": "consolidated-00250-of-00272.safetensors",
+ "layers.6.experts.72.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.72.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.73.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.74.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.75.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.76.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.77.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.78.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.79.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.8.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.80.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.81.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.82.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.83.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.84.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.85.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.86.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.87.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.88.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.89.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.9.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.90.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.91.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.92.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.93.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.94.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.95.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.96.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.97.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w1.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w1.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w2.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w2.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w3.weight": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.98.w3.weight_scale": "consolidated-00251-of-00272.safetensors",
+ "layers.6.experts.99.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.experts.99.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.6.experts.99.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.experts.99.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.6.experts.99.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.experts.99.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.6.ffn_norm.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.gate.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.6.shared_experts.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.kv_a_norm.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.q_a_norm.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wkv_a_with_mqa.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wkv_b.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wkv_b.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wo.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wo.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wq_a.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wq_b.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention.wq_b.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.attention_norm.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.0.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.1.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.10.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.100.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.101.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.102.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.103.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.104.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.105.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.106.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.107.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.108.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.109.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.11.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.110.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.111.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.112.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.113.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.114.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.115.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.116.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.117.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.118.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w1.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w1.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w2.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w2.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w3.weight": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.119.w3.weight_scale": "consolidated-00252-of-00272.safetensors",
+ "layers.60.experts.12.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.12.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.12.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.12.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.12.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.12.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.120.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.121.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.122.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.123.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.124.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.125.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.126.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.127.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.13.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.14.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.15.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.16.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.17.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.18.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.19.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.2.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.20.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.21.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.22.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.23.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.24.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.25.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.26.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.27.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.28.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.29.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w2.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w2.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w3.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.3.w3.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.30.w1.weight": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.30.w1.weight_scale": "consolidated-00253-of-00272.safetensors",
+ "layers.60.experts.30.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.30.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.30.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.30.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.31.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.32.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.33.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.34.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.35.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.36.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.37.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.38.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.39.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.4.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.40.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.41.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.42.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.43.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.44.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.45.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.46.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.47.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.48.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.49.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.5.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.50.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.51.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.52.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.53.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.54.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w3.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.55.w3.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.56.w1.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.56.w1.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.56.w2.weight": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.56.w2.weight_scale": "consolidated-00254-of-00272.safetensors",
+ "layers.60.experts.56.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.56.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.57.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.58.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.59.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.6.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.60.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.61.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.62.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.63.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.64.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.65.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.66.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.67.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.68.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.69.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.7.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.70.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.71.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.72.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.73.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.74.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.75.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.76.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.77.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.78.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.79.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.8.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.80.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w1.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w1.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w2.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w2.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w3.weight": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.81.w3.weight_scale": "consolidated-00255-of-00272.safetensors",
+ "layers.60.experts.82.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.82.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.82.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.82.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.82.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.82.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.83.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.84.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.85.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.86.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.87.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.88.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.89.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.9.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.90.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.91.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.92.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.93.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.94.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.95.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.96.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.97.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.98.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.experts.99.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.ffn_norm.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.gate.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.60.shared_experts.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.kv_a_norm.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.q_a_norm.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wkv_a_with_mqa.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wkv_b.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wkv_b.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wo.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wo.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wq_a.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wq_b.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention.wq_b.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.attention_norm.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.0.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.1.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.10.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.100.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.101.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w1.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w1.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w2.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w2.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w3.weight": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.102.w3.weight_scale": "consolidated-00256-of-00272.safetensors",
+ "layers.7.experts.103.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.103.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.103.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.103.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.103.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.103.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.104.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.105.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.106.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.107.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.108.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.109.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.11.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.110.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.111.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.112.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.113.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.114.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.115.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.116.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.117.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.118.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.119.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.12.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.120.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.121.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.122.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.123.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.124.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.125.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.126.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.127.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w2.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w2.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w3.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.13.w3.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.14.w1.weight": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.14.w1.weight_scale": "consolidated-00257-of-00272.safetensors",
+ "layers.7.experts.14.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.14.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.14.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.14.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.15.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.16.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.17.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.18.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.19.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.2.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.20.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.21.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.22.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.23.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.24.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.25.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.26.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.27.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.28.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.29.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.3.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.30.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.31.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.32.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.33.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.34.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.35.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.36.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.37.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.38.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w3.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.39.w3.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.4.w1.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.4.w1.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.4.w2.weight": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.4.w2.weight_scale": "consolidated-00258-of-00272.safetensors",
+ "layers.7.experts.4.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.4.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.40.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.41.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.42.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.43.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.44.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.45.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.46.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.47.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.48.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.49.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.5.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.50.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.51.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.52.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.53.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.54.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.55.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.56.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.57.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.58.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.59.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.6.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.60.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.61.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.62.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.63.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.64.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w1.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w1.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w2.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w2.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w3.weight": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.65.w3.weight_scale": "consolidated-00259-of-00272.safetensors",
+ "layers.7.experts.66.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.66.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.66.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.66.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.66.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.66.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.67.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.68.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.69.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.7.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.70.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.71.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.72.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.73.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.74.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.75.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.76.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.77.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.78.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.79.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.8.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.80.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.81.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.82.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.83.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.84.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.85.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.86.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.87.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.88.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.89.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.9.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w2.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w2.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w3.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.90.w3.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.91.w1.weight": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.91.w1.weight_scale": "consolidated-00260-of-00272.safetensors",
+ "layers.7.experts.91.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.91.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.91.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.91.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.92.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.93.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.94.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.95.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.96.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.97.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.98.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.experts.99.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.ffn_norm.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.gate.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.7.shared_experts.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.kv_a_norm.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.q_a_norm.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wkv_a_with_mqa.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wkv_b.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wkv_b.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wo.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wo.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wq_a.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wq_b.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention.wq_b.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.attention_norm.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.0.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.1.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.10.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.100.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.101.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.102.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.103.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.104.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.105.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.106.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.107.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.108.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.109.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.11.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.110.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w2.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w2.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w3.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.111.w3.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.112.w1.weight": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.112.w1.weight_scale": "consolidated-00261-of-00272.safetensors",
+ "layers.8.experts.112.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.112.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.112.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.112.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.113.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.114.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.115.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.116.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.117.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.118.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.119.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.12.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.120.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.121.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.122.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.123.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.124.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.125.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.126.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.127.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.13.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.14.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.15.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.16.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.17.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.18.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.19.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.2.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.20.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.21.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w3.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.22.w3.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.23.w1.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.23.w1.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.23.w2.weight": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.23.w2.weight_scale": "consolidated-00262-of-00272.safetensors",
+ "layers.8.experts.23.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.23.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.24.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.25.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.26.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.27.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.28.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.29.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.3.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.30.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.31.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.32.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.33.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.34.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.35.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.36.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.37.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.38.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.39.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.4.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.40.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.41.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.42.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.43.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.44.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.45.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.46.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.47.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.48.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w1.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w1.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w2.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w2.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w3.weight": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.49.w3.weight_scale": "consolidated-00263-of-00272.safetensors",
+ "layers.8.experts.5.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.5.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.5.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.5.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.5.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.5.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.50.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.51.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.52.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.53.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.54.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.55.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.56.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.57.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.58.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.59.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.6.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.60.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.61.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.62.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.63.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.64.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.65.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.66.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.67.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.68.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.69.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.7.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.70.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.71.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.72.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.73.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w2.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w2.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w3.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.74.w3.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.75.w1.weight": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.75.w1.weight_scale": "consolidated-00264-of-00272.safetensors",
+ "layers.8.experts.75.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.75.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.75.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.75.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.76.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.77.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.78.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.79.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.8.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.80.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.81.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.82.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.83.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.84.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.85.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.86.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.87.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.88.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.89.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.9.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.90.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.91.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.92.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.93.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.94.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.95.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.96.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.97.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.98.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.experts.99.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.ffn_norm.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.gate.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w1.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w1.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w2.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w2.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w3.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.8.shared_experts.w3.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.kv_a_norm.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.q_a_norm.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.wkv_a_with_mqa.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.wkv_b.weight": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.wkv_b.weight_scale": "consolidated-00265-of-00272.safetensors",
+ "layers.9.attention.wo.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.attention.wo.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.attention.wq_a.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.attention.wq_b.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.attention.wq_b.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.attention_norm.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.0.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.1.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.10.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.100.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.101.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.102.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.103.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.104.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.105.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.106.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.107.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.108.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.109.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.11.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.110.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.111.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.112.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.113.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.114.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.115.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.116.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.117.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.118.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.119.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.12.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w2.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w2.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w3.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.120.w3.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.121.w1.weight": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.121.w1.weight_scale": "consolidated-00266-of-00272.safetensors",
+ "layers.9.experts.121.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.121.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.121.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.121.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.122.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.123.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.124.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.125.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.126.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.127.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.13.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.14.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.15.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.16.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.17.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.18.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.19.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.2.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.20.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.21.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.22.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.23.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.24.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.25.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.26.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.27.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.28.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.29.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.3.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.30.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w3.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.31.w3.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.32.w1.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.32.w1.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.32.w2.weight": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.32.w2.weight_scale": "consolidated-00267-of-00272.safetensors",
+ "layers.9.experts.32.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.32.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.33.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.34.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.35.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.36.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.37.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.38.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.39.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.4.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.40.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.41.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.42.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.43.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.44.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.45.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.46.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.47.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.48.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.49.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.5.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.50.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.51.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.52.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.53.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.54.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.55.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.56.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.57.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w1.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w1.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w2.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w2.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w3.weight": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.58.w3.weight_scale": "consolidated-00268-of-00272.safetensors",
+ "layers.9.experts.59.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.59.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.59.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.59.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.59.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.59.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.6.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.60.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.61.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.62.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.63.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.64.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.65.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.66.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.67.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.68.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.69.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.7.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.70.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.71.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.72.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.73.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.74.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.75.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.76.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.77.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.78.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.79.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.8.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.80.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.81.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.82.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w2.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w2.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w3.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.83.w3.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.84.w1.weight": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.84.w1.weight_scale": "consolidated-00269-of-00272.safetensors",
+ "layers.9.experts.84.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.84.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.84.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.84.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.85.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.86.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.87.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.88.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.89.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.9.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.90.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.91.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.92.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.93.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.94.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.95.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.96.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.97.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.98.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.experts.99.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.ffn_norm.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.gate.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w1.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w1.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w2.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w2.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w3.weight": "consolidated-00270-of-00272.safetensors",
+ "layers.9.shared_experts.w3.weight_scale": "consolidated-00270-of-00272.safetensors",
+ "norm.weight": "consolidated-00272-of-00272.safetensors",
+ "output.weight": "consolidated-00272-of-00272.safetensors",
+ "patch_merger.merging_layer.weight": "consolidated-00270-of-00272.safetensors",
+ "pre_mm_projector_norm.weight": "consolidated-00270-of-00272.safetensors",
+ "tok_embeddings.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.ln_pre.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.patch_conv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.0.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.1.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.10.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.11.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.12.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.13.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.14.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.15.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.16.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.17.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.18.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.19.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.2.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.20.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.21.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.22.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.23.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.24.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.25.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.26.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.27.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.28.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.29.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.3.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.30.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.31.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.32.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.33.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.34.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.attention.wk.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.attention.wo.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.attention.wq.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.attention.wv.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.attention_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.feed_forward.w1.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.feed_forward.w2.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.feed_forward.w3.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.35.ffn_norm.weight": "consolidated-00271-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.36.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.37.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.38.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.39.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.4.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.40.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.41.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.42.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.43.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.44.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.45.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.46.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.47.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.5.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.6.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.7.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.8.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.attention.wk.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.attention.wo.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.attention.wq.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.attention.wv.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.attention_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.feed_forward.w1.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.feed_forward.w2.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.feed_forward.w3.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_encoder.transformer.layers.9.ffn_norm.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_language_adapter.w_in.weight": "consolidated-00272-of-00272.safetensors",
+ "vision_language_adapter.w_out.weight": "consolidated-00272-of-00272.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/params.json b/params.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfa6e7c365975c4737bc5436ebd84d960c0c0fc8
--- /dev/null
+++ b/params.json
@@ -0,0 +1,117 @@
+{
+ "dim": 7168,
+ "head_dim": 192,
+ "hidden_dim": 16384,
+ "kv_lora_rank": 512,
+ "llama_4_scaling": {
+ "beta": 0.1,
+ "original_max_position_embeddings": 8192
+ },
+ "max_position_embeddings": 294912,
+ "max_seq_len": 262144,
+ "moe": {
+ "expert_hidden_dim": 4096,
+ "expert_model_parallel": 1,
+ "expert_parallel": 1,
+ "first_k_dense_replace": 3,
+ "num_expert_groups": 1,
+ "num_expert_groups_per_tok": 1,
+ "num_experts": 128,
+ "num_experts_per_tok": 4,
+ "num_shared_experts": 1,
+ "route_every_n": 1,
+ "routed_scale": 1.0
+ },
+ "n_heads": 128,
+ "n_kv_heads": 128,
+ "n_layers": 61,
+ "norm_eps": 1e-06,
+ "q_lora_rank": 1536,
+ "qk_nope_head_dim": 128,
+ "qk_rope_head_dim": 64,
+ "quantization_config": {
+ "config_groups": {
+ "FP8_BLOCK": {
+ "format": "float-quantized",
+ "input_activations": {
+ "actorder": null,
+ "block_structure": null,
+ "dynamic": true,
+ "group_size": 128,
+ "num_bits": 8,
+ "observer": null,
+ "observer_kwargs": {},
+ "strategy": "group",
+ "symmetric": true,
+ "type": "float"
+ },
+ "output_activations": null,
+ "targets": [
+ "Linear"
+ ],
+ "weights": {
+ "actorder": null,
+ "block_structure": [
+ 128,
+ 128
+ ],
+ "dynamic": false,
+ "group_size": null,
+ "num_bits": 8,
+ "observer": "static_minmax",
+ "observer_kwargs": {},
+ "strategy": "block",
+ "symmetric": true,
+ "type": "float"
+ }
+ }
+ },
+ "format": "float-quantized",
+ "global_compression_ratio": null,
+ "ignore": [
+ "model.embed_tokens",
+ "re:patch_merger.*",
+ "re:vision_encoder.*",
+ "re:vision_language_adapter.*",
+ "re:.*kv_a_proj_with_mqa$",
+ "re:.*q_a_proj$",
+ "re:.*gate$",
+ "lm_head"
+ ],
+ "kv_cache_scheme": null,
+ "quant_method": "compressed-tensors",
+ "quantization_status": "compressed",
+ "sparsity_config": {},
+ "transform_config": {},
+ "version": "0.12.3.dev29+g73c2cf9.d20251119"
+ },
+ "rope_theta": 10000.0,
+ "tied_embeddings": false,
+ "v_head_dim": 128,
+ "vision_encoder": {
+ "adapter_bias": false,
+ "add_pre_mm_projector_layer_norm": true,
+ "hidden_size": 1664,
+ "image_break_token_id": 12,
+ "image_end_token_id": 13,
+ "image_size": 1540,
+ "image_token_id": 10,
+ "intermediate_size": 8192,
+ "max_image_size": 1540,
+ "mm_projector_id": "patch_merge",
+ "num_attention_heads": 16,
+ "num_channels": 3,
+ "num_hidden_layers": 48,
+ "patch_size": 14,
+ "rope_theta": 10000.0,
+ "spatial_merge_size": 2
+ },
+ "vocab_size": 131072,
+ "yarn": {
+ "alpha": 1,
+ "apply_scale": false,
+ "beta": 32,
+ "factor": 36,
+ "original_max_position_embeddings": 8192
+ }
+}
diff --git a/processor_config.json b/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a37d728b12fd27ac60a437894bd51de83449bf30
--- /dev/null
+++ b/processor_config.json
@@ -0,0 +1,42 @@
+{
+ "image_break_token": "[IMG_BREAK]",
+ "image_end_token": "[IMG_END]",
+ "image_processor": {
+ "crop_size": null,
+ "data_format": "channels_first",
+ "device": null,
+ "disable_grouping": null,
+ "do_center_crop": null,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_pad": null,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "image_processor_type": "PixtralImageProcessorFast",
+ "image_seq_length": null,
+ "image_std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ],
+ "input_data_format": null,
+ "pad_size": null,
+ "patch_size": 14,
+ "processor_class": "PixtralProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_tensors": null,
+ "size": {
+ "longest_edge": 1540
+ }
+ },
+ "image_token": "[IMG]",
+ "patch_size": 14,
+ "processor_class": "PixtralProcessor",
+ "spatial_merge_size": 2
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a339be8e293fc04bace0e5ec4ca86c7990a618d
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,7014 @@
+{
+ "additional_special_tokens": [
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[INST]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[/INST]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[AVAILABLE_TOOLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[/AVAILABLE_TOOLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[TOOL_RESULTS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[/TOOL_RESULTS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[TOOL_CALLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[IMG]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[IMG_BREAK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[IMG_END]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[PREFIX]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[MIDDLE]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[SUFFIX]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[SYSTEM_PROMPT]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[/SYSTEM_PROMPT]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[TOOL_CONTENT]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[AUDIO]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[BEGIN_AUDIO]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[ARGS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[CALL_ID]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[THINK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "[/THINK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ {
+ "content": "