config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "Qwen2_5_VLForConditionalGeneration" |
| 4 | ], |
| 5 | "attention_dropout": 0.0, |
| 6 | "bos_token_id": 151643, |
| 7 | "eos_token_id": 151645, |
| 8 | "vision_start_token_id": 151652, |
| 9 | "vision_end_token_id": 151653, |
| 10 | "vision_token_id": 151654, |
| 11 | "image_token_id": 151655, |
| 12 | "video_token_id": 151656, |
| 13 | "hidden_act": "silu", |
| 14 | "hidden_size": 2048, |
| 15 | "initializer_range": 0.02, |
| 16 | "intermediate_size": 11008, |
| 17 | "max_position_embeddings": 128000, |
| 18 | "max_window_layers": 70, |
| 19 | "model_type": "qwen2_5_vl", |
| 20 | "num_attention_heads": 16, |
| 21 | "num_hidden_layers": 36, |
| 22 | "num_key_value_heads": 2, |
| 23 | "rms_norm_eps": 1e-06, |
| 24 | "rope_theta": 1000000.0, |
| 25 | "sliding_window": 32768, |
| 26 | "tie_word_embeddings": true, |
| 27 | "torch_dtype": "bfloat16", |
| 28 | "transformers_version": "4.41.2", |
| 29 | "use_cache": true, |
| 30 | "use_sliding_window": false, |
| 31 | "vision_config": { |
| 32 | "depth": 32, |
| 33 | "hidden_act": "silu", |
| 34 | "hidden_size": 1280, |
| 35 | "intermediate_size": 3420, |
| 36 | "num_heads": 16, |
| 37 | "in_chans": 3, |
| 38 | "out_hidden_size": 2048, |
| 39 | "patch_size": 14, |
| 40 | "spatial_merge_size": 2, |
| 41 | "spatial_patch_size": 14, |
| 42 | "window_size": 112, |
| 43 | "fullatt_block_indexes": [ |
| 44 | 7, |
| 45 | 15, |
| 46 | 23, |
| 47 | 31 |
| 48 | ], |
| 49 | "tokens_per_second": 2, |
| 50 | "temporal_patch_size": 2 |
| 51 | }, |
| 52 | "rope_scaling": { |
| 53 | "type": "mrope", |
| 54 | "mrope_section": [ |
| 55 | 16, |
| 56 | 24, |
| 57 | 24 |
| 58 | ] |
| 59 | }, |
| 60 | "vocab_size": 151936 |
| 61 | } |