tokenizer_config.json
| 1 | { |
| 2 | "add_eos_token": true, |
| 3 | "add_prefix_space": false, |
| 4 | "added_tokens_decoder": { |
| 5 | "151643": { |
| 6 | "content": "<|endoftext|>", |
| 7 | "lstrip": false, |
| 8 | "normalized": false, |
| 9 | "rstrip": false, |
| 10 | "single_word": false, |
| 11 | "special": true |
| 12 | }, |
| 13 | "151644": { |
| 14 | "content": "<|im_start|>", |
| 15 | "lstrip": false, |
| 16 | "normalized": false, |
| 17 | "rstrip": false, |
| 18 | "single_word": false, |
| 19 | "special": true |
| 20 | }, |
| 21 | "151645": { |
| 22 | "content": "<|im_end|>", |
| 23 | "lstrip": false, |
| 24 | "normalized": false, |
| 25 | "rstrip": false, |
| 26 | "single_word": false, |
| 27 | "special": true |
| 28 | } |
| 29 | }, |
| 30 | "additional_special_tokens": [ |
| 31 | "<|im_start|>", |
| 32 | "<|im_end|>" |
| 33 | ], |
| 34 | "auto_map": { |
| 35 | "AutoTokenizer": [ |
| 36 | "tokenization_qwen.Qwen2Tokenizer", |
| 37 | "tokenization_qwen.Qwen2TokenizerFast" |
| 38 | ] |
| 39 | }, |
| 40 | "bos_token": null, |
| 41 | "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", |
| 42 | "clean_up_tokenization_spaces": false, |
| 43 | "eos_token": "<|endoftext|>", |
| 44 | "errors": "replace", |
| 45 | "extra_special_tokens": {}, |
| 46 | "model_max_length": 32768, |
| 47 | "pad_token": "<|endoftext|>", |
| 48 | "split_special_tokens": false, |
| 49 | "tokenizer_class": "Qwen2Tokenizer", |
| 50 | "unk_token": null |
| 51 | } |
| 52 | |