{ "_name_or_path": "/data5/zww//Llama-3.2-90B-Vision-Instruct", "architectures": [ "MllamaForConditionalGeneration" ], "image_token_index": 128256, "model_type": "mllama", "quantization_config": { "amp": true, "autoround_version": "0.4.0.dev", "backend": "auto_round:gptq:exllamav2", "batch_size": 1, "bits": 4, "data_type": "int", "dataset": "liuhaotian/llava", "enable_minmax_tuning": true, "enable_norm_bias_tuning": false, "enable_quanted_input": true, "gradient_accumulate_steps": 8, "group_size": 128, "iters": 200, "low_gpu_mem_usage": true, "lr": 0.005, "minmax_lr": 0.005, "nsamples": 512, "quant_method": "intel/auto-round", "scale_dtype": "torch.float16", "seqlen": 512, "sym": true, "to_quant_block_names": [ [ "language_model.model.layers.0", "language_model.model.layers.1", "language_model.model.layers.2", "language_model.model.layers.3", "language_model.model.layers.4", "language_model.model.layers.5", "language_model.model.layers.6", "language_model.model.layers.7", "language_model.model.layers.8", "language_model.model.layers.9", "language_model.model.layers.10", "language_model.model.layers.11", "language_model.model.layers.12", "language_model.model.layers.13", "language_model.model.layers.14", "language_model.model.layers.15", "language_model.model.layers.16", "language_model.model.layers.17", "language_model.model.layers.18", "language_model.model.layers.19", "language_model.model.layers.20", "language_model.model.layers.21", "language_model.model.layers.22", "language_model.model.layers.23", "language_model.model.layers.24", "language_model.model.layers.25", "language_model.model.layers.26", "language_model.model.layers.27", "language_model.model.layers.28", "language_model.model.layers.29", "language_model.model.layers.30", "language_model.model.layers.31", "language_model.model.layers.32", "language_model.model.layers.33", "language_model.model.layers.34", "language_model.model.layers.35", "language_model.model.layers.36", "language_model.model.layers.37", "language_model.model.layers.38", "language_model.model.layers.39", "language_model.model.layers.40", "language_model.model.layers.41", "language_model.model.layers.42", "language_model.model.layers.43", "language_model.model.layers.44", "language_model.model.layers.45", "language_model.model.layers.46", "language_model.model.layers.47", "language_model.model.layers.48", "language_model.model.layers.49", "language_model.model.layers.50", "language_model.model.layers.51", "language_model.model.layers.52", "language_model.model.layers.53", "language_model.model.layers.54", "language_model.model.layers.55", "language_model.model.layers.56", "language_model.model.layers.57", "language_model.model.layers.58", "language_model.model.layers.59", "language_model.model.layers.60", "language_model.model.layers.61", "language_model.model.layers.62", "language_model.model.layers.63", "language_model.model.layers.64", "language_model.model.layers.65", "language_model.model.layers.66", "language_model.model.layers.67", "language_model.model.layers.68", "language_model.model.layers.69", "language_model.model.layers.70", "language_model.model.layers.71", "language_model.model.layers.72", "language_model.model.layers.73", "language_model.model.layers.74", "language_model.model.layers.75", "language_model.model.layers.76", "language_model.model.layers.77", "language_model.model.layers.78", "language_model.model.layers.79", "language_model.model.layers.80", "language_model.model.layers.81", "language_model.model.layers.82", "language_model.model.layers.83", "language_model.model.layers.84", "language_model.model.layers.85", "language_model.model.layers.86", "language_model.model.layers.87", "language_model.model.layers.88", "language_model.model.layers.89", "language_model.model.layers.90", "language_model.model.layers.91", "language_model.model.layers.92", "language_model.model.layers.93", "language_model.model.layers.94", "language_model.model.layers.95", "language_model.model.layers.96", "language_model.model.layers.97", "language_model.model.layers.98", "language_model.model.layers.99" ] ] }, "text_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "cross_attention_layers": [ 3, 8, 13, 18, 23, 28, 33, 38, 43, 48, 53, 58, 63, 68, 73, 78, 83, 88, 93, 98 ], "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [ 128001, 128008, 128009 ], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 8192, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 28672, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "mllama_text_model", "no_repeat_ngram_size": 0, "num_attention_heads": 64, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 100, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 128004, "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_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "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": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 128256 }, "torch_dtype": "bfloat16", "transformers_version": "4.46.1", "vision_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_heads": 16, "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": "gelu", "hidden_size": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 560, "initializer_range": 0.02, "intermediate_layers_indices": [ 3, 7, 15, 23, 30 ], "intermediate_size": 5120, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_num_tiles": 4, "min_length": 0, "model_type": "mllama_vision_model", "no_repeat_ngram_size": 0, "norm_eps": 1e-05, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_global_layers": 8, "num_hidden_layers": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "supported_aspect_ratios": [ [ 1, 1 ], [ 1, 2 ], [ 1, 3 ], [ 1, 4 ], [ 2, 1 ], [ 2, 2 ], [ 3, 1 ], [ 4, 1 ] ], "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": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vision_output_dim": 7680 } }