| { |
| "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 |
| } |
|
|
