Upload GPTQ-quantized SmolVLM-Instruct (4-bit)

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,355 @@
+{
+  "architectures": [
+    "Idefics3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_seq_len": 81,
+  "image_token_id": 49153,
+  "model_type": "idefics3",
+  "pad_token_id": 128002,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": "static",
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.vision_model.encoder.layers.0.self_attn.k_proj",
+      "model.vision_model.encoder.layers.0.self_attn.v_proj",
+      "model.vision_model.encoder.layers.0.self_attn.q_proj",
+      "model.vision_model.encoder.layers.0.self_attn.out_proj",
+      "model.vision_model.encoder.layers.0.mlp.fc1",
+      "model.vision_model.encoder.layers.0.mlp.fc2",
+      "model.vision_model.encoder.layers.1.self_attn.k_proj",
+      "model.vision_model.encoder.layers.1.self_attn.v_proj",
+      "model.vision_model.encoder.layers.1.self_attn.q_proj",
+      "model.vision_model.encoder.layers.1.self_attn.out_proj",
+      "model.vision_model.encoder.layers.1.mlp.fc1",
+      "model.vision_model.encoder.layers.1.mlp.fc2",
+      "model.vision_model.encoder.layers.2.self_attn.k_proj",
+      "model.vision_model.encoder.layers.2.self_attn.v_proj",
+      "model.vision_model.encoder.layers.2.self_attn.q_proj",
+      "model.vision_model.encoder.layers.2.self_attn.out_proj",
+      "model.vision_model.encoder.layers.2.mlp.fc1",
+      "model.vision_model.encoder.layers.2.mlp.fc2",
+      "model.vision_model.encoder.layers.3.self_attn.k_proj",
+      "model.vision_model.encoder.layers.3.self_attn.v_proj",
+      "model.vision_model.encoder.layers.3.self_attn.q_proj",
+      "model.vision_model.encoder.layers.3.self_attn.out_proj",
+      "model.vision_model.encoder.layers.3.mlp.fc1",
+      "model.vision_model.encoder.layers.3.mlp.fc2",
+      "model.vision_model.encoder.layers.4.self_attn.k_proj",
+      "model.vision_model.encoder.layers.4.self_attn.v_proj",
+      "model.vision_model.encoder.layers.4.self_attn.q_proj",
+      "model.vision_model.encoder.layers.4.self_attn.out_proj",
+      "model.vision_model.encoder.layers.4.mlp.fc1",
+      "model.vision_model.encoder.layers.4.mlp.fc2",
+      "model.vision_model.encoder.layers.5.self_attn.k_proj",
+      "model.vision_model.encoder.layers.5.self_attn.v_proj",
+      "model.vision_model.encoder.layers.5.self_attn.q_proj",
+      "model.vision_model.encoder.layers.5.self_attn.out_proj",
+      "model.vision_model.encoder.layers.5.mlp.fc1",
+      "model.vision_model.encoder.layers.5.mlp.fc2",
+      "model.vision_model.encoder.layers.6.self_attn.k_proj",
+      "model.vision_model.encoder.layers.6.self_attn.v_proj",
+      "model.vision_model.encoder.layers.6.self_attn.q_proj",
+      "model.vision_model.encoder.layers.6.self_attn.out_proj",
+      "model.vision_model.encoder.layers.6.mlp.fc1",
+      "model.vision_model.encoder.layers.6.mlp.fc2",
+      "model.vision_model.encoder.layers.7.self_attn.k_proj",
+      "model.vision_model.encoder.layers.7.self_attn.v_proj",
+      "model.vision_model.encoder.layers.7.self_attn.q_proj",
+      "model.vision_model.encoder.layers.7.self_attn.out_proj",
+      "model.vision_model.encoder.layers.7.mlp.fc1",
+      "model.vision_model.encoder.layers.7.mlp.fc2",
+      "model.vision_model.encoder.layers.8.self_attn.k_proj",
+      "model.vision_model.encoder.layers.8.self_attn.v_proj",
+      "model.vision_model.encoder.layers.8.self_attn.q_proj",
+      "model.vision_model.encoder.layers.8.self_attn.out_proj",
+      "model.vision_model.encoder.layers.8.mlp.fc1",
+      "model.vision_model.encoder.layers.8.mlp.fc2",
+      "model.vision_model.encoder.layers.9.self_attn.k_proj",
+      "model.vision_model.encoder.layers.9.self_attn.v_proj",
+      "model.vision_model.encoder.layers.9.self_attn.q_proj",
+      "model.vision_model.encoder.layers.9.self_attn.out_proj",
+      "model.vision_model.encoder.layers.9.mlp.fc1",
+      "model.vision_model.encoder.layers.9.mlp.fc2",
+      "model.vision_model.encoder.layers.10.self_attn.k_proj",
+      "model.vision_model.encoder.layers.10.self_attn.v_proj",
+      "model.vision_model.encoder.layers.10.self_attn.q_proj",
+      "model.vision_model.encoder.layers.10.self_attn.out_proj",
+      "model.vision_model.encoder.layers.10.mlp.fc1",
+      "model.vision_model.encoder.layers.10.mlp.fc2",
+      "model.vision_model.encoder.layers.11.self_attn.k_proj",
+      "model.vision_model.encoder.layers.11.self_attn.v_proj",
+      "model.vision_model.encoder.layers.11.self_attn.q_proj",
+      "model.vision_model.encoder.layers.11.self_attn.out_proj",
+      "model.vision_model.encoder.layers.11.mlp.fc1",
+      "model.vision_model.encoder.layers.11.mlp.fc2",
+      "model.vision_model.encoder.layers.12.self_attn.k_proj",
+      "model.vision_model.encoder.layers.12.self_attn.v_proj",
+      "model.vision_model.encoder.layers.12.self_attn.q_proj",
+      "model.vision_model.encoder.layers.12.self_attn.out_proj",
+      "model.vision_model.encoder.layers.12.mlp.fc1",
+      "model.vision_model.encoder.layers.12.mlp.fc2",
+      "model.vision_model.encoder.layers.13.self_attn.k_proj",
+      "model.vision_model.encoder.layers.13.self_attn.v_proj",
+      "model.vision_model.encoder.layers.13.self_attn.q_proj",
+      "model.vision_model.encoder.layers.13.self_attn.out_proj",
+      "model.vision_model.encoder.layers.13.mlp.fc1",
+      "model.vision_model.encoder.layers.13.mlp.fc2",
+      "model.vision_model.encoder.layers.14.self_attn.k_proj",
+      "model.vision_model.encoder.layers.14.self_attn.v_proj",
+      "model.vision_model.encoder.layers.14.self_attn.q_proj",
+      "model.vision_model.encoder.layers.14.self_attn.out_proj",
+      "model.vision_model.encoder.layers.14.mlp.fc1",
+      "model.vision_model.encoder.layers.14.mlp.fc2",
+      "model.vision_model.encoder.layers.15.self_attn.k_proj",
+      "model.vision_model.encoder.layers.15.self_attn.v_proj",
+      "model.vision_model.encoder.layers.15.self_attn.q_proj",
+      "model.vision_model.encoder.layers.15.self_attn.out_proj",
+      "model.vision_model.encoder.layers.15.mlp.fc1",
+      "model.vision_model.encoder.layers.15.mlp.fc2",
+      "model.vision_model.encoder.layers.16.self_attn.k_proj",
+      "model.vision_model.encoder.layers.16.self_attn.v_proj",
+      "model.vision_model.encoder.layers.16.self_attn.q_proj",
+      "model.vision_model.encoder.layers.16.self_attn.out_proj",
+      "model.vision_model.encoder.layers.16.mlp.fc1",
+      "model.vision_model.encoder.layers.16.mlp.fc2",
+      "model.vision_model.encoder.layers.17.self_attn.k_proj",
+      "model.vision_model.encoder.layers.17.self_attn.v_proj",
+      "model.vision_model.encoder.layers.17.self_attn.q_proj",
+      "model.vision_model.encoder.layers.17.self_attn.out_proj",
+      "model.vision_model.encoder.layers.17.mlp.fc1",
+      "model.vision_model.encoder.layers.17.mlp.fc2",
+      "model.vision_model.encoder.layers.18.self_attn.k_proj",
+      "model.vision_model.encoder.layers.18.self_attn.v_proj",
+      "model.vision_model.encoder.layers.18.self_attn.q_proj",
+      "model.vision_model.encoder.layers.18.self_attn.out_proj",
+      "model.vision_model.encoder.layers.18.mlp.fc1",
+      "model.vision_model.encoder.layers.18.mlp.fc2",
+      "model.vision_model.encoder.layers.19.self_attn.k_proj",
+      "model.vision_model.encoder.layers.19.self_attn.v_proj",
+      "model.vision_model.encoder.layers.19.self_attn.q_proj",
+      "model.vision_model.encoder.layers.19.self_attn.out_proj",
+      "model.vision_model.encoder.layers.19.mlp.fc1",
+      "model.vision_model.encoder.layers.19.mlp.fc2",
+      "model.vision_model.encoder.layers.20.self_attn.k_proj",
+      "model.vision_model.encoder.layers.20.self_attn.v_proj",
+      "model.vision_model.encoder.layers.20.self_attn.q_proj",
+      "model.vision_model.encoder.layers.20.self_attn.out_proj",
+      "model.vision_model.encoder.layers.20.mlp.fc1",
+      "model.vision_model.encoder.layers.20.mlp.fc2",
+      "model.vision_model.encoder.layers.21.self_attn.k_proj",
+      "model.vision_model.encoder.layers.21.self_attn.v_proj",
+      "model.vision_model.encoder.layers.21.self_attn.q_proj",
+      "model.vision_model.encoder.layers.21.self_attn.out_proj",
+      "model.vision_model.encoder.layers.21.mlp.fc1",
+      "model.vision_model.encoder.layers.21.mlp.fc2",
+      "model.vision_model.encoder.layers.22.self_attn.k_proj",
+      "model.vision_model.encoder.layers.22.self_attn.v_proj",
+      "model.vision_model.encoder.layers.22.self_attn.q_proj",
+      "model.vision_model.encoder.layers.22.self_attn.out_proj",
+      "model.vision_model.encoder.layers.22.mlp.fc1",
+      "model.vision_model.encoder.layers.22.mlp.fc2",
+      "model.vision_model.encoder.layers.23.self_attn.k_proj",
+      "model.vision_model.encoder.layers.23.self_attn.v_proj",
+      "model.vision_model.encoder.layers.23.self_attn.q_proj",
+      "model.vision_model.encoder.layers.23.self_attn.out_proj",
+      "model.vision_model.encoder.layers.23.mlp.fc1",
+      "model.vision_model.encoder.layers.23.mlp.fc2",
+      "model.vision_model.encoder.layers.24.self_attn.k_proj",
+      "model.vision_model.encoder.layers.24.self_attn.v_proj",
+      "model.vision_model.encoder.layers.24.self_attn.q_proj",
+      "model.vision_model.encoder.layers.24.self_attn.out_proj",
+      "model.vision_model.encoder.layers.24.mlp.fc1",
+      "model.vision_model.encoder.layers.24.mlp.fc2",
+      "model.vision_model.encoder.layers.25.self_attn.k_proj",
+      "model.vision_model.encoder.layers.25.self_attn.v_proj",
+      "model.vision_model.encoder.layers.25.self_attn.q_proj",
+      "model.vision_model.encoder.layers.25.self_attn.out_proj",
+      "model.vision_model.encoder.layers.25.mlp.fc1",
+      "model.vision_model.encoder.layers.25.mlp.fc2",
+      "model.vision_model.encoder.layers.26.self_attn.k_proj",
+      "model.vision_model.encoder.layers.26.self_attn.v_proj",
+      "model.vision_model.encoder.layers.26.self_attn.q_proj",
+      "model.vision_model.encoder.layers.26.self_attn.out_proj",
+      "model.vision_model.encoder.layers.26.mlp.fc1",
+      "model.vision_model.encoder.layers.26.mlp.fc2",
+      "model.connector.modality_projection.proj",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {}
+  },
+  "scale_factor": 3,
+  "text_config": {
+    "_attn_implementation_autoset": false,
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "/fsx/m4/experiments/local_experiment_dir/s3_async_temporary_checkpoint_folder/tr_324_opt_400/unwrapped_model",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "dtype": "bfloat16",
+    "eos_token_id": 0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 16384,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 32,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 32,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "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": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pretraining_tp": 1,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 273768.0,
+    "use_cache": true,
+    "use_resampler": false,
+    "vocab_size": 49155
+  },
+  "tie_word_embeddings": false,
+  "transformers.js_config": {
+    "dtype": {
+      "decoder_model_merged": "q4",
+      "embed_tokens": "auto",
+      "vision_encoder": "auto"
+    },
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "decoder_model_merged.onnx": true,
+      "decoder_model_merged_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vision_config": {
+    "_attn_implementation_autoset": false,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "max_image_size": {
+      "longest_edge": 384
+    },
+    "model_type": "idefics3_vision",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "size": {
+      "longest_edge": 1920
+    },
+    "tie_word_embeddings": false
+  },
+  "vocab_size": 49155
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 49154,
+  "pad_token_id": 2,
+  "transformers_version": "4.57.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c839593ef0414471848487b6f2bf99a2a994cce5c6cdc41f6f934f98cd64d99
+size 2101921576