tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "audio_bos_token": "<|audio_start|>", |
| 4 | "audio_eos_token": "<|audio_end|>", |
| 5 | "audio_token": "<|audio_pad|>", |
| 6 | "backend": "tokenizers", |
| 7 | "bos_token": null, |
| 8 | "clean_up_tokenization_spaces": false, |
| 9 | "eos_token": "<|im_end|>", |
| 10 | "errors": "replace", |
| 11 | "extra_special_tokens": [ |
| 12 | "<|im_start|>", |
| 13 | "<|im_end|>", |
| 14 | "<|object_ref_start|>", |
| 15 | "<|object_ref_end|>", |
| 16 | "<|box_start|>", |
| 17 | "<|box_end|>", |
| 18 | "<|quad_start|>", |
| 19 | "<|quad_end|>", |
| 20 | "<|vision_start|>", |
| 21 | "<|vision_end|>", |
| 22 | "<|vision_pad|>", |
| 23 | "<|image_pad|>", |
| 24 | "<|video_pad|>" |
| 25 | ], |
| 26 | "image_token": "<|image_pad|>", |
| 27 | "is_local": true, |
| 28 | "local_files_only": false, |
| 29 | "model_max_length": 262144, |
| 30 | "model_specific_special_tokens": { |
| 31 | "audio_bos_token": "<|audio_start|>", |
| 32 | "audio_eos_token": "<|audio_end|>", |
| 33 | "audio_token": "<|audio_pad|>", |
| 34 | "image_token": "<|image_pad|>", |
| 35 | "video_token": "<|video_pad|>", |
| 36 | "vision_bos_token": "<|vision_start|>", |
| 37 | "vision_eos_token": "<|vision_end|>" |
| 38 | }, |
| 39 | "pad_token": "<|endoftext|>", |
| 40 | "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", |
| 41 | "split_special_tokens": false, |
| 42 | "tokenizer_class": "Qwen2Tokenizer", |
| 43 | "unk_token": null, |
| 44 | "video_token": "<|video_pad|>", |
| 45 | "vision_bos_token": "<|vision_start|>", |
| 46 | "vision_eos_token": "<|vision_end|>" |
| 47 | } |
| 48 | |