{ "_name_or_path": "/mnt/nas1/daoze/code/swift/output/llava1_6-llama3_1-8b-instruct-my/v30-20240821-191548/checkpoint-1315", "architectures": [ "LlavaNextForConditionalGeneration" ], "hidden_size": 4096, "ignore_index": -100, "image_grid_pinpoints": [ [ 336, 672 ], [ 672, 336 ], [ 672, 672 ], [ 1008, 336 ], [ 336, 1008 ] ], "image_token_index": 128255, "model_type": "llava_next", "projector_hidden_act": "gelu", "text_config": { "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 128000, "eos_token_id": [ 128001, 128008, 128009 ], "intermediate_size": 14336, "max_position_embeddings": 131072, "model_type": "llama", "num_key_value_heads": 8, "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, "torch_dtype": "bfloat16", "vocab_size": 128256 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.43.4", "use_cache": false, "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 }