| { | |
| "_name_or_path": "/nm/drive1/shubhra/huggingface/hub/models--mgoin--pixtral-12b/snapshots/b688e8c2462a6cbd6da504a332fb3167be928128", | |
| "architectures": [ | |
| "LlavaForConditionalGeneration" | |
| ], | |
| "ignore_index": -100, | |
| "image_seq_length": 1, | |
| "image_token_index": 10, | |
| "model_type": "llava", | |
| "projector_hidden_act": "gelu", | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "int" | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "int-quantized", | |
| "global_compression_ratio": 1.254986373686197, | |
| "ignore": [ | |
| "vision_tower.transformer.layers.0.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.0.attention.k_proj", | |
| "vision_tower.transformer.layers.0.attention.v_proj", | |
| "vision_tower.transformer.layers.0.attention.q_proj", | |
| "vision_tower.transformer.layers.0.attention.o_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.1.attention.k_proj", | |
| "vision_tower.transformer.layers.1.attention.v_proj", | |
| "vision_tower.transformer.layers.1.attention.q_proj", | |
| "vision_tower.transformer.layers.1.attention.o_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.2.attention.k_proj", | |
| "vision_tower.transformer.layers.2.attention.v_proj", | |
| "vision_tower.transformer.layers.2.attention.q_proj", | |
| "vision_tower.transformer.layers.2.attention.o_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.3.attention.k_proj", | |
| "vision_tower.transformer.layers.3.attention.v_proj", | |
| "vision_tower.transformer.layers.3.attention.q_proj", | |
| "vision_tower.transformer.layers.3.attention.o_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.4.attention.k_proj", | |
| "vision_tower.transformer.layers.4.attention.v_proj", | |
| "vision_tower.transformer.layers.4.attention.q_proj", | |
| "vision_tower.transformer.layers.4.attention.o_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.5.attention.k_proj", | |
| "vision_tower.transformer.layers.5.attention.v_proj", | |
| "vision_tower.transformer.layers.5.attention.q_proj", | |
| "vision_tower.transformer.layers.5.attention.o_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.6.attention.k_proj", | |
| "vision_tower.transformer.layers.6.attention.v_proj", | |
| "vision_tower.transformer.layers.6.attention.q_proj", | |
| "vision_tower.transformer.layers.6.attention.o_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.7.attention.k_proj", | |
| "vision_tower.transformer.layers.7.attention.v_proj", | |
| "vision_tower.transformer.layers.7.attention.q_proj", | |
| "vision_tower.transformer.layers.7.attention.o_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.8.attention.k_proj", | |
| "vision_tower.transformer.layers.8.attention.v_proj", | |
| "vision_tower.transformer.layers.8.attention.q_proj", | |
| "vision_tower.transformer.layers.8.attention.o_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.9.attention.k_proj", | |
| "vision_tower.transformer.layers.9.attention.v_proj", | |
| "vision_tower.transformer.layers.9.attention.q_proj", | |
| "vision_tower.transformer.layers.9.attention.o_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.10.attention.k_proj", | |
| "vision_tower.transformer.layers.10.attention.v_proj", | |
| "vision_tower.transformer.layers.10.attention.q_proj", | |
| "vision_tower.transformer.layers.10.attention.o_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.11.attention.k_proj", | |
| "vision_tower.transformer.layers.11.attention.v_proj", | |
| "vision_tower.transformer.layers.11.attention.q_proj", | |
| "vision_tower.transformer.layers.11.attention.o_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.12.attention.k_proj", | |
| "vision_tower.transformer.layers.12.attention.v_proj", | |
| "vision_tower.transformer.layers.12.attention.q_proj", | |
| "vision_tower.transformer.layers.12.attention.o_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.13.attention.k_proj", | |
| "vision_tower.transformer.layers.13.attention.v_proj", | |
| "vision_tower.transformer.layers.13.attention.q_proj", | |
| "vision_tower.transformer.layers.13.attention.o_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.14.attention.k_proj", | |
| "vision_tower.transformer.layers.14.attention.v_proj", | |
| "vision_tower.transformer.layers.14.attention.q_proj", | |
| "vision_tower.transformer.layers.14.attention.o_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.15.attention.k_proj", | |
| "vision_tower.transformer.layers.15.attention.v_proj", | |
| "vision_tower.transformer.layers.15.attention.q_proj", | |
| "vision_tower.transformer.layers.15.attention.o_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.16.attention.k_proj", | |
| "vision_tower.transformer.layers.16.attention.v_proj", | |
| "vision_tower.transformer.layers.16.attention.q_proj", | |
| "vision_tower.transformer.layers.16.attention.o_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.17.attention.k_proj", | |
| "vision_tower.transformer.layers.17.attention.v_proj", | |
| "vision_tower.transformer.layers.17.attention.q_proj", | |
| "vision_tower.transformer.layers.17.attention.o_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.18.attention.k_proj", | |
| "vision_tower.transformer.layers.18.attention.v_proj", | |
| "vision_tower.transformer.layers.18.attention.q_proj", | |
| "vision_tower.transformer.layers.18.attention.o_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.19.attention.k_proj", | |
| "vision_tower.transformer.layers.19.attention.v_proj", | |
| "vision_tower.transformer.layers.19.attention.q_proj", | |
| "vision_tower.transformer.layers.19.attention.o_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.20.attention.k_proj", | |
| "vision_tower.transformer.layers.20.attention.v_proj", | |
| "vision_tower.transformer.layers.20.attention.q_proj", | |
| "vision_tower.transformer.layers.20.attention.o_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.21.attention.k_proj", | |
| "vision_tower.transformer.layers.21.attention.v_proj", | |
| "vision_tower.transformer.layers.21.attention.q_proj", | |
| "vision_tower.transformer.layers.21.attention.o_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.22.attention.k_proj", | |
| "vision_tower.transformer.layers.22.attention.v_proj", | |
| "vision_tower.transformer.layers.22.attention.q_proj", | |
| "vision_tower.transformer.layers.22.attention.o_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.23.attention.k_proj", | |
| "vision_tower.transformer.layers.23.attention.v_proj", | |
| "vision_tower.transformer.layers.23.attention.q_proj", | |
| "vision_tower.transformer.layers.23.attention.o_proj", | |
| "multi_modal_projector.linear_1", | |
| "multi_modal_projector.linear_2", | |
| "language_model.lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "text_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": 1, | |
| "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": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "is_composition": true, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 1024000, | |
| "min_length": 0, | |
| "model_type": "mistral", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 32, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "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": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000000.0, | |
| "sep_token_id": null, | |
| "sliding_window": null, | |
| "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, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "vision_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, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 1024, | |
| "intermediate_size": 4096, | |
| "is_composition": true, | |
| "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": "pixtral", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rope_theta": 10000.0, | |
| "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": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } |