tokenizer_config.json
| 1 | { |
| 2 | "bos_token": "<s>", |
| 3 | "clean_up_tokenization_spaces": true, |
| 4 | "cls_token": "<s>", |
| 5 | "eos_token": "</s>", |
| 6 | "mask_token": { |
| 7 | "__type": "AddedToken", |
| 8 | "content": "<mask>", |
| 9 | "lstrip": true, |
| 10 | "normalized": true, |
| 11 | "rstrip": false, |
| 12 | "single_word": false |
| 13 | }, |
| 14 | "model_max_length": 512, |
| 15 | "pad_token": "<pad>", |
| 16 | "sep_token": "</s>", |
| 17 | "sp_model_kwargs": {}, |
| 18 | "tokenizer_class": "XLMRobertaTokenizer", |
| 19 | "unk_token": "<unk>" |
| 20 | } |
| 21 | |