tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": true, |
| 3 | "added_tokens_decoder": { |
| 4 | "0": { |
| 5 | "content": "<s>", |
| 6 | "lstrip": false, |
| 7 | "normalized": false, |
| 8 | "rstrip": false, |
| 9 | "single_word": false, |
| 10 | "special": true |
| 11 | }, |
| 12 | "1": { |
| 13 | "content": "<pad>", |
| 14 | "lstrip": false, |
| 15 | "normalized": false, |
| 16 | "rstrip": false, |
| 17 | "single_word": false, |
| 18 | "special": true |
| 19 | }, |
| 20 | "2": { |
| 21 | "content": "</s>", |
| 22 | "lstrip": false, |
| 23 | "normalized": false, |
| 24 | "rstrip": false, |
| 25 | "single_word": false, |
| 26 | "special": true |
| 27 | }, |
| 28 | "3": { |
| 29 | "content": "<unk>", |
| 30 | "lstrip": false, |
| 31 | "normalized": false, |
| 32 | "rstrip": false, |
| 33 | "single_word": false, |
| 34 | "special": true |
| 35 | }, |
| 36 | "4": { |
| 37 | "content": "<mask>", |
| 38 | "lstrip": true, |
| 39 | "normalized": false, |
| 40 | "rstrip": false, |
| 41 | "single_word": false, |
| 42 | "special": true |
| 43 | } |
| 44 | }, |
| 45 | "bos_token": "<s>", |
| 46 | "clean_up_tokenization_spaces": true, |
| 47 | "cls_token": "<s>", |
| 48 | "eos_token": "</s>", |
| 49 | "errors": "replace", |
| 50 | "mask_token": "<mask>", |
| 51 | "model_max_length": 1000000000000000019884624838656, |
| 52 | "pad_token": "<pad>", |
| 53 | "sep_token": "</s>", |
| 54 | "tokenizer_class": "RobertaTokenizer", |
| 55 | "trim_offsets": true, |
| 56 | "unk_token": "<unk>" |
| 57 | } |
| 58 | |