Upload MLX converted model with quantization settings

README.md

@@ -0,0 +1,42 @@
+---
+license: other
+license_name: modified-mit
+library_name: transformers
+base_model: moonshotai/Kimi-K2-Instruct-0905
+tags:
+- mlx
+---
+
+# cs2764/Kimi-K2-Instruct-0905-mlx-3Bit-gs32
+
+The Model [cs2764/Kimi-K2-Instruct-0905-mlx-3Bit-gs32](https://huggingface.co/cs2764/Kimi-K2-Instruct-0905-mlx-3Bit-gs32) was converted to MLX format from [moonshotai/Kimi-K2-Instruct-0905](https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905) using mlx-lm version **0.28.0**.
+
+## Quantization Details
+
+This model was converted with the following quantization settings:
+
+- **Quantization Strategy**: 3-bit quantization
+- **Group Size**: 32
+- **Average bits per weight**: 4.002
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("cs2764/Kimi-K2-Instruct-0905-mlx-3Bit-gs32")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,46 @@
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>
+  # Tools
+  {{ tools | tojson }}<|im_end|>
+{%- endif -%}
+{%- for message in messages -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+    <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+  {%- endif -%}
+  
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {% endif %}
+
+  {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}
+    {%- if message['content'] -%}{{ message['content'] }}{%- endif -%}
+    <|tool_calls_section_begin|>
+    {%- for tool_call in message['tool_calls'] -%}
+      {%- set formatted_id = tool_call['id'] -%}
+      <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+    {%- endfor -%}
+    <|tool_calls_section_end|>
+  {%- elif message['role'] == 'tool' -%}
+    ## Return of {{ message.tool_call_id }}
+    {{ message['content'] }}
+  {%- elif message['content'] is string -%}
+    {{ message['content'] }}
+  {%- elif message['content'] is not none -%}
+    {% for content in message['content'] -%}
+      {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+        <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+      {% else -%}
+        {{ content['text'] }}
+      {%- endif -%}
+    {%- endfor -%}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+{%- endif -%}

config.json

@@ -0,0 +1,126 @@
+{
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
+    "architectures": [
+        "DeepseekV3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+        "AutoModel": "modeling_deepseek.DeepseekV3Model",
+        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 163584,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 163585,
+    "ep_size": 1,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "first_k_dense_replace": 1,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kv_lora_rank": 512,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 262144,
+    "min_length": 0,
+    "model_type": "kimi_k2",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 384,
+    "n_shared_experts": 1,
+    "no_repeat_ngram_size": 0,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 0,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 163839,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization": {
+        "group_size": 32,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "beta_fast": 1.0,
+        "beta_slow": 1.0,
+        "factor": 64.0,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 50000.0,
+    "routed_scaling_factor": 2.827,
+    "scoring_func": "sigmoid",
+    "sep_token_id": null,
+    "seq_aux": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.51.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840
+}

configuration_deepseek.py

@@ -0,0 +1,212 @@
+# Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_length": 131072,
+  "eos_token_id": 163586
+}

model-00001-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0aafac8f2772e55fb9d30038f96555ef906d88900bae337f8f759b00042a1eb
+size 3705120655

model-00002-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfb89d01e6444d344b71d43deb0726861df06cc82d837cfb4581d42d966b71d
+size 5284823701

model-00003-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1081465f39fc4bc247476aae8933d49d73fdb03a4b85f541b8681be1edb049bd
+size 5362947782

model-00004-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b989e98bcc8619cb1cd5892732f897b0aa6ee8e8f0e7aefc97d72042d4116e
+size 3601340056

model-00005-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e486f24af026838e1dc35199602e390732a4d57f1d21fe3eca73637f0bac0d
+size 5284823702

model-00006-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ff5e8d3e6cafe63eaa5e2f91a4650ed3372031f210ab3882b02c6d3f609a3c
+size 5362947781

model-00007-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90625b7411aac0e6542fea263d40f0d95bf9e392c4051299fe0ffe96a342286
+size 3523216023

model-00008-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2857841ceecc2bf6bdf4764600e50d5c68d19d8645c9aaba2f0c6aeb72ad90
+size 5362947781

model-00009-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3451a4bd8d06023253975fd4fa0bbb385da71cd718925d0f5879885f4c68eba0
+size 5284823704

model-00010-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1e3f6c5537078feeb9619296b1ae6c051c748e8f23c3c8227331361064cb03
+size 3601340102

model-00011-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fc0598714c4e9377cc700ee7a922d2fbbb9f5154a6f501b6e80bded3fa9922
+size 5284823703

model-00012-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044e51786a003d17fde4a3cbfb7f7ce020495eb396e1a79b90cc7907fdd3307f
+size 5362947778

model-00013-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2f5487ac1e279273e761380d89437f009959631a8a9438589c1e05340cd280
+size 3601340014

model-00014-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaca4a54a4d9a22a64afd9096b7e65cfa953297e8cb6affddfb9e8e0d33ad45f
+size 5284823704

model-00015-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e26d9f4b40c21d0321e262d7aba84c3598b013e49769a5b73101ccda4586a5
+size 5362947693

model-00016-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19094ff25a55efaa1a50109bc92d4ba28d435eda67065735f51020ae42ed47ab
+size 3523216025

model-00017-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b897934b6a22325ee4986ae222e08e6e09ac68e2e53f5069141cfb52ddf9aa3
+size 5362947802

model-00018-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f30607481a34fa055ee8feb725f52ae1531de8abf4db21c8377afe2421c62eb
+size 5284823705

model-00019-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4b499e2fb6084c32db858f9b2f6811e4849349464f0af7c2f0a8ac489488f1
+size 3601340113

model-00020-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e4f1d434bbc13f539772013237d3a5afe8bacf29e38197b76712fb67e40621
+size 5284823706

model-00021-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5201dfcefb8146f3a3dac73655b397a750f48c8eef4eecdf375e5ecc0c0736
+size 5362947775

model-00022-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b928224a43609bada3a70350ce3b8748de9d63d96f72878862099aa49d1693d
+size 3601340079

model-00023-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1539757e49858e406e4260eebc1f85ad7aace923a8b4c9276a391bc122bb3c41
+size 5284823707

model-00024-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484303cf7cbe740558956ff013c545998a09193244c98e388cfe8266fc93ac8c
+size 5362947750

model-00025-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430ce725564db6363c1630b1661b03265655fde762f9751d23d7137a25512928
+size 3523216026

model-00026-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ef20342b2876d8ba510970212525c56a920cf5d5263f996ee0114012c954f9
+size 5362947794

model-00027-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4dd817417977afe845f4ba67ed6713cd6cf3c1508e97cf141d5287b64475d48
+size 5284823709

model-00028-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0348d24c4ec71020f599ce0805c1bb26d16f6cfd83b87cefcfa1769aa552891
+size 3601340135

model-00029-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107cf2aeb522b46f6ec86d82a69f1085b76603f835a8b4f81af3f0bccdd33580
+size 5284823708

model-00030-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f91611fd7d16ba430284427a6a399d38feb7fa10617043a06df04da879fe03
+size 5362947817

model-00031-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d496191af17819179510c2cbf0bdbe055069546bf1b6935bfd18852f8293c857
+size 3601340031

model-00032-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ace9b608325cc2465ac5243abef3fa707aa19acc05469000cf83677841bbc11
+size 5284823711

model-00033-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb9bda4ac637153e153ae2f9d61e2e951ea9d4ee1026254ecc82d9e4cd983b0
+size 5362947816

model-00034-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4954a66e5836037c9dd228cf77987325a3a21fe98aaf72e6a40d796e1987d6e2
+size 3523216026

model-00035-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff7a77440b2587ef3c433129eb7427a44d491be5dd617dc4302c2dd30a369ae
+size 5362947816

model-00036-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e45b9db9e78b1e5f1ac20cbed0decb5f0d6b2d093e810d54c5b114ffbf33bb
+size 5284823709

model-00037-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab70db5c2e357c5a0d142cffd33e10271b44c728e63187f1157b1a403ba4d7a7
+size 3601340123

model-00038-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65873dd054794f6b39b3a4ad3bc952144e7f272e53ea44a972b2f575afd6ccbd
+size 5284823708

model-00039-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1416ece911016c2017d618b193ec25f0aafa5e2ff70c849659402e1fdc1e266e
+size 5362947817

model-00040-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dee871309766ee5d288207630195aee256157b097cab7a12d137227ab986286
+size 3601340015

model-00041-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519d7978ba441b08044fe34f5fa0643819cb0f82bba5ae3627bc7621053ffd87
+size 5284823707

model-00042-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ebf3c4ec8da67e1229254040178beea300bdb731bea2d2dab89da5a897d325
+size 5362947742

model-00043-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1399666998f3ce4e32c5bc8ce3b854ab2859c956e2b969525574122f67cdb36
+size 3523216026

model-00044-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62668a9741b8cf66b9cb52c31f20e6073d12b30ac54fe90460f65bd93d284d8c
+size 5362947730

model-00045-of-00109.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3649f4c67227b59509bcf08fa1e6b59300478a30c4ad233502e37bfa56ee7d5b
+size 5284823709