tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "backend": "tokenizers", |
| 4 | "bos_token": null, |
| 5 | "clean_up_tokenization_spaces": false, |
| 6 | "eos_token": "<|im_end|>", |
| 7 | "errors": "replace", |
| 8 | "extra_special_tokens": [ |
| 9 | "<|denoise|>", |
| 10 | "<|lang_start|>", |
| 11 | "<|lang_end|>", |
| 12 | "<|instruct_start|>", |
| 13 | "<|instruct_end|>", |
| 14 | "<|text_start|>", |
| 15 | "<|text_end|>" |
| 16 | ], |
| 17 | "is_local": true, |
| 18 | "model_max_length": 131072, |
| 19 | "pad_token": "<|endoftext|>", |
| 20 | "split_special_tokens": false, |
| 21 | "tokenizer_class": "Qwen2Tokenizer", |
| 22 | "unk_token": null |
| 23 | } |
| 24 | |