{ "architectures": [ "LlavaQwen3_5ViTForConditionalGeneration" ], "bos_token_id": null, "dtype": "bfloat16", "eos_token_id": 151645, "hidden_size": 2560, "image_grid_pinpoints": [ [ 384, 384 ], [ 384, 768 ], [ 384, 1152 ], [ 384, 1536 ], [ 384, 1920 ], [ 384, 2304 ], [ 768, 384 ], [ 768, 768 ], [ 768, 1152 ], [ 768, 1536 ], [ 768, 1920 ], [ 768, 2304 ], [ 1152, 384 ], [ 1152, 768 ], [ 1152, 1152 ], [ 1152, 1536 ], [ 1152, 1920 ], [ 1152, 2304 ], [ 1536, 384 ], [ 1536, 768 ], [ 1536, 1152 ], [ 1536, 1536 ], [ 1536, 1920 ], [ 1536, 2304 ], [ 1920, 384 ], [ 1920, 768 ], [ 1920, 1152 ], [ 1920, 1536 ], [ 1920, 1920 ], [ 1920, 2304 ], [ 2304, 384 ], [ 2304, 768 ], [ 2304, 1152 ], [ 2304, 1536 ], [ 2304, 1920 ], [ 2304, 2304 ] ], "image_token_index": 151669, "model_type": "llava_qwen3_5vit_qwen3", "multimodal_projector_bias": true, "pad_token_id": 151643, "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "/share/m2v_intern_v3/wangjunjie09/model_cache/huggingface/Qwen/Qwen3-4B-Instruct-2507", "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 262144, "max_window_layers": 36, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 5000000, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151936 }, "tie_word_embeddings": true, "transformers_version": "5.5.4", "use_cache": false, "video_token_index": 151670, "vision_aspect_ratio": "anyres_max_9", "vision_config": { "deepstack_visual_indexes": [], "depth": 24, "dtype": "bfloat16", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1024, "image_size": 384, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "qwen3_5", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 2048, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_feature_layer": -1, "vision_feature_select_strategy": "full", "auto_map": { "AutoConfig": "modeling_qwen3_5vit_qwen3.LlavaQwen3_5ViTConfig", "AutoModel": "modeling_qwen3_5vit_qwen3.LlavaQwen3_5ViTForConditionalGeneration", "AutoModelForCausalLM": "modeling_qwen3_5vit_qwen3.LlavaQwen3_5ViTForConditionalGeneration", "AutoModelForImageTextToText": "modeling_qwen3_5vit_qwen3.LlavaQwen3_5ViTForConditionalGeneration" } }