{ "base_model_name_or_path": null, "is_lora": false, "mesh_und_connector_dropout": 0.0, "mesh_und_connector_file": "mesh_und_connector.safetensors", "mesh_und_connector_hidden_dims": [ 1024, 2048 ], "mesh_und_encoder_file": "mesh_und_encoder.safetensors", "mesh_und_encoder_type": "frozen_mesh_und_transformer", "mesh_und_pointnum": 8192, "mesh_und_token": "<|mesh_und_pad|>", "mesh_und_token_id": 151684, "mesh_und_token_len": 513, "mesh_und_use_color": true, "model_type": "eva01", "qwen3vl_config": { "architectures": [ "Qwen3VLForConditionalGeneration" ], "dtype": "bfloat16", "image_token_id": 151655, "model_type": "qwen3_vl", "text_config": { "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": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "tie_word_embeddings": true, "use_cache": true, "vocab_size": 151936 }, "tie_word_embeddings": true, "transformers_version": "4.57.0", "use_cache": false, "video_token_id": 151656, "vision_config": { "deepstack_visual_indexes": [ 5, 11, 17 ], "depth": 24, "dtype": "bfloat16", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1024, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "qwen3_vl", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 2048, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }, "training_recipe": "alignment_then_instruction_tuning", "transformers_version": "5.8.1" }