tokenizer_config.json
| 1 | { |
| 2 | "added_tokens_decoder": { |
| 3 | "0": { |
| 4 | "content": "<s>", |
| 5 | "lstrip": false, |
| 6 | "normalized": false, |
| 7 | "rstrip": false, |
| 8 | "single_word": false, |
| 9 | "special": true |
| 10 | }, |
| 11 | "1": { |
| 12 | "content": "<pad>", |
| 13 | "lstrip": false, |
| 14 | "normalized": false, |
| 15 | "rstrip": false, |
| 16 | "single_word": false, |
| 17 | "special": true |
| 18 | }, |
| 19 | "2": { |
| 20 | "content": "</s>", |
| 21 | "lstrip": false, |
| 22 | "normalized": false, |
| 23 | "rstrip": false, |
| 24 | "single_word": false, |
| 25 | "special": true |
| 26 | }, |
| 27 | "3": { |
| 28 | "content": "<unk>", |
| 29 | "lstrip": false, |
| 30 | "normalized": true, |
| 31 | "rstrip": false, |
| 32 | "single_word": false, |
| 33 | "special": true |
| 34 | }, |
| 35 | "104": { |
| 36 | "content": "[UNK]", |
| 37 | "lstrip": false, |
| 38 | "normalized": false, |
| 39 | "rstrip": false, |
| 40 | "single_word": false, |
| 41 | "special": true |
| 42 | }, |
| 43 | "30526": { |
| 44 | "content": "<mask>", |
| 45 | "lstrip": true, |
| 46 | "normalized": false, |
| 47 | "rstrip": false, |
| 48 | "single_word": false, |
| 49 | "special": true |
| 50 | } |
| 51 | }, |
| 52 | "bos_token": "<s>", |
| 53 | "clean_up_tokenization_spaces": true, |
| 54 | "cls_token": "<s>", |
| 55 | "do_lower_case": true, |
| 56 | "eos_token": "</s>", |
| 57 | "mask_token": "<mask>", |
| 58 | "max_length": 250, |
| 59 | "model_max_length": 512, |
| 60 | "pad_to_multiple_of": null, |
| 61 | "pad_token": "<pad>", |
| 62 | "pad_token_type_id": 0, |
| 63 | "padding_side": "right", |
| 64 | "sep_token": "</s>", |
| 65 | "stride": 0, |
| 66 | "strip_accents": null, |
| 67 | "tokenize_chinese_chars": true, |
| 68 | "tokenizer_class": "MPNetTokenizer", |
| 69 | "truncation_side": "right", |
| 70 | "truncation_strategy": "longest_first", |
| 71 | "unk_token": "[UNK]" |
| 72 | } |
| 73 | |