tokenizer_config.json
| 1 | { |
| 2 | "add_bos_token": false, |
| 3 | "add_eos_token": false, |
| 4 | "bos_token": { |
| 5 | "__type": "AddedToken", |
| 6 | "content": "<｜begin▁of▁sentence｜>", |
| 7 | "lstrip": false, |
| 8 | "normalized": true, |
| 9 | "rstrip": false, |
| 10 | "single_word": false |
| 11 | }, |
| 12 | "clean_up_tokenization_spaces": false, |
| 13 | "eos_token": { |
| 14 | "__type": "AddedToken", |
| 15 | "content": "<｜end▁of▁sentence｜>", |
| 16 | "lstrip": false, |
| 17 | "normalized": true, |
| 18 | "rstrip": false, |
| 19 | "single_word": false |
| 20 | }, |
| 21 | "legacy": true, |
| 22 | "model_max_length": 131072, |
| 23 | "pad_token": { |
| 24 | "__type": "AddedToken", |
| 25 | "content": "<｜end▁of▁sentence｜>", |
| 26 | "lstrip": false, |
| 27 | "normalized": true, |
| 28 | "rstrip": false, |
| 29 | "single_word": false |
| 30 | }, |
| 31 | "sp_model_kwargs": {}, |
| 32 | "unk_token": null, |
| 33 | "tokenizer_class": "LlamaTokenizerFast" |
| 34 | } |