Feng613/SleepVLM-3B

1{2  "architectures": [3    "Qwen2_5_VLForConditionalGeneration"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "dtype": "bfloat16",8  "eos_token_id": 151645,9  "hidden_act": "silu",10  "hidden_size": 2048,11  "image_token_id": 151655,12  "initializer_range": 0.02,13  "intermediate_size": 11008,14  "max_position_embeddings": 128000,15  "max_window_layers": 70,16  "model_type": "qwen2_5_vl",17  "num_attention_heads": 16,18  "num_hidden_layers": 36,19  "num_key_value_heads": 2,20  "rms_norm_eps": 1e-06,21  "rope_scaling": {22    "mrope_section": [23      16,24      24,25      2426    ],27    "rope_type": "default",28    "type": "default"29  },30  "rope_theta": 1000000.0,31  "sliding_window": 32768,32  "text_config": {33    "_name_or_path": "./models/Qwen2.5-VL-3B-Instruct",34    "architectures": [35      "Qwen2_5_VLForConditionalGeneration"36    ],37    "attention_dropout": 0.0,38    "bos_token_id": 151643,39    "dtype": "bfloat16",40    "eos_token_id": 151645,41    "hidden_act": "silu",42    "hidden_size": 2048,43    "initializer_range": 0.02,44    "intermediate_size": 11008,45    "layer_types": [46      "full_attention",47      "full_attention",48      "full_attention",49      "full_attention",50      "full_attention",51      "full_attention",52      "full_attention",53      "full_attention",54      "full_attention",55      "full_attention",56      "full_attention",57      "full_attention",58      "full_attention",59      "full_attention",60      "full_attention",61      "full_attention",62      "full_attention",63      "full_attention",64      "full_attention",65      "full_attention",66      "full_attention",67      "full_attention",68      "full_attention",69      "full_attention",70      "full_attention",71      "full_attention",72      "full_attention",73      "full_attention",74      "full_attention",75      "full_attention",76      "full_attention",77      "full_attention",78      "full_attention",79      "full_attention",80      "full_attention",81      "full_attention"82    ],83    "max_position_embeddings": 128000,84    "max_window_layers": 70,85    "model_type": "qwen2_5_vl_text",86    "num_attention_heads": 16,87    "num_hidden_layers": 36,88    "num_key_value_heads": 2,89    "rms_norm_eps": 1e-06,90    "rope_scaling": {91      "mrope_section": [92        16,93        24,94        2495      ],96      "rope_type": "default",97      "type": "default"98    },99    "rope_theta": 1000000.0,100    "sliding_window": null,101    "tie_word_embeddings": true,102    "use_cache": true,103    "use_sliding_window": false,104    "vision_token_id": 151654,105    "vocab_size": 151936106  },107  "transformers_version": "4.57.3",108  "use_cache": true,109  "use_sliding_window": false,110  "video_token_id": 151656,111  "vision_config": {112    "depth": 32,113    "dtype": "bfloat16",114    "fullatt_block_indexes": [115      7,116      15,117      23,118      31119    ],120    "hidden_act": "silu",121    "hidden_size": 1280,122    "in_channels": 3,123    "in_chans": 3,124    "initializer_range": 0.02,125    "intermediate_size": 3420,126    "model_type": "qwen2_5_vl",127    "num_heads": 16,128    "out_hidden_size": 2048,129    "patch_size": 14,130    "spatial_merge_size": 2,131    "spatial_patch_size": 14,132    "temporal_patch_size": 2,133    "tokens_per_second": 2,134    "window_size": 112135  },136  "vision_end_token_id": 151653,137  "vision_start_token_id": 151652,138  "vision_token_id": 151654,139  "vocab_size": 151936140}141