config.json
| 1 | { |
| 2 | "_name_or_path": "/home/notebook/data/group/wth/QualityReasoning/Models/Qwen2.5-VL-7B-Instruct", |
| 3 | "architectures": [ |
| 4 | "Qwen2_5_VLForConditionalGeneration" |
| 5 | ], |
| 6 | "attention_dropout": 0.0, |
| 7 | "bos_token_id": 151643, |
| 8 | "eos_token_id": 151645, |
| 9 | "hidden_act": "silu", |
| 10 | "hidden_size": 3584, |
| 11 | "image_token_id": 151655, |
| 12 | "initializer_range": 0.02, |
| 13 | "intermediate_size": 18944, |
| 14 | "max_position_embeddings": 128000, |
| 15 | "max_window_layers": 28, |
| 16 | "model_type": "qwen2_5_vl", |
| 17 | "num_attention_heads": 28, |
| 18 | "num_hidden_layers": 28, |
| 19 | "num_key_value_heads": 4, |
| 20 | "rms_norm_eps": 1e-06, |
| 21 | "rope_scaling": { |
| 22 | "mrope_section": [ |
| 23 | 16, |
| 24 | 24, |
| 25 | 24 |
| 26 | ], |
| 27 | "rope_type": "default", |
| 28 | "type": "default" |
| 29 | }, |
| 30 | "rope_theta": 1000000.0, |
| 31 | "sliding_window": 32768, |
| 32 | "tie_word_embeddings": false, |
| 33 | "torch_dtype": "bfloat16", |
| 34 | "transformers_version": "4.49.0", |
| 35 | "use_cache": false, |
| 36 | "use_sliding_window": false, |
| 37 | "video_token_id": 151656, |
| 38 | "vision_config": { |
| 39 | "hidden_size": 1280, |
| 40 | "in_chans": 3, |
| 41 | "model_type": "qwen2_5_vl", |
| 42 | "spatial_patch_size": 14, |
| 43 | "tokens_per_second": 2, |
| 44 | "torch_dtype": "bfloat16" |
| 45 | }, |
| 46 | "vision_end_token_id": 151653, |
| 47 | "vision_start_token_id": 151652, |
| 48 | "vision_token_id": 151654, |
| 49 | "vocab_size": 152064 |
| 50 | } |
| 51 | |