{ "architectures": [ "LlavaNextForConditionalGeneration" ], "ignore_index": -100, "image_grid_pinpoints": [ [ 336, 672 ], [ 672, 336 ], [ 672, 672 ], [ 1008, 336 ], [ 336, 1008 ] ], "image_token_index": 32000, "model_type": "llava_next", "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2", "architectures": [ "MistralForCausalLM" ], "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "torch_dtype": "bfloat16", "vocab_size": 32064 }, "torch_dtype": "float16", "transformers_version": "4.39.0.dev0", "use_image_newline_parameter": true, "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 }