{ "architectures": [ "Mistral3ForConditionalGeneration" ], "image_token_index": 10, "model_type": "mistral3", "multimodal_projector_bias": false, "projector_hidden_act": "gelu", "quantization_config": { "act_bits": 32, "amp": true, "autoround_version": "0.4.6", "batch_size": 8, "bits": 4, "data_type": "int", "dataset": "NeelNanda/pile-10k", "enable_minmax_tuning": true, "enable_norm_bias_tuning": false, "enable_quanted_input": true, "gradient_accumulate_steps": 1, "group_size": 128, "iters": 200, "low_gpu_mem_usage": false, "lr": 0.005, "minmax_lr": 0.005, "modules_to_not_convert": [ "vision_tower.transformer.layers", "multi_modal_projector.patch_merger.merging_layer", "multi_modal_projector.linear_1", "multi_modal_projector.linear_2", "language_model.lm_head" ], "nsamples": 128, "quant_method": "awq", "scale_dtype": "torch.float16", "seqlen": 2048, "sym": true, "to_quant_block_names": "language_model.model.layers", "version": "gemm", "zero_point": false }, "spatial_merge_size": 2, "text_config": { "attention_dropout": 0.0, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 32768, "max_position_embeddings": 131072, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000000.0, "sliding_window": null, "use_cache": true, "vocab_size": 131072 }, "torch_dtype": "float16", "transformers_version": "4.50.0.dev0", "vision_config": { "attention_dropout": 0.0, "head_dim": 64, "hidden_act": "gelu", "hidden_size": 1024, "image_size": 1540, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "pixtral", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": 14, "rope_theta": 10000.0 }, "vision_feature_layer": -1 }