| { | |
| "_name_or_path": "Shure-Dev/llava-vima", | |
| "architectures": [ | |
| "LlavaForConditionalGeneration" | |
| ], | |
| "ignore_index": -100, | |
| "image_token_index": 32000, | |
| "model_type": "llava", | |
| "pad_token_id": 32001, | |
| "projector_hidden_act": "gelu", | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float32", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "text_config": { | |
| "_name_or_path": "mistralai/Mistral-7B-v0.1", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "sliding_window": 4096, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 32064 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "vision_config": { | |
| "hidden_size": 1024, | |
| "image_size": 336, | |
| "intermediate_size": 4096, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768, | |
| "vocab_size": 32000 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "default", | |
| "vocab_size": 32064 | |
| } | |