| { | |
| "architectures": [ | |
| "Mistral3ForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_index": 10, | |
| "model_type": "mistral3", | |
| "multimodal_projector_bias": false, | |
| "projector_hidden_act": "gelu", | |
| "quantization_config": { | |
| "autoround_version": "0.9.0", | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "data_type": "int", | |
| "dataset": "liuhaotian/llava_conv_58k", | |
| "gradient_accumulate_steps": 8, | |
| "group_size": 128, | |
| "packing_format": "auto_round:auto_gptq", | |
| "quant_method": "auto-round", | |
| "scale_dtype": "None", | |
| "seqlen": 512, | |
| "sym": true | |
| }, | |
| "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 | |
| }, | |
| "transformers_version": "4.57.1", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "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 | |
| } | |