| { |
| "bos_token": { |
| "__type": "AddedToken", |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "clean_up_tokenization_spaces": true, |
| "cls_token": { |
| "__type": "AddedToken", |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "do_basic_tokenize": true, |
| "do_lower_case": true, |
| "eos_token": { |
| "__type": "AddedToken", |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "mask_token": { |
| "__type": "AddedToken", |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "model_max_length": 512, |
| "never_split": null, |
| "pad_token": { |
| "__type": "AddedToken", |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "sep_token": { |
| "__type": "AddedToken", |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "strip_accents": null, |
| "tokenize_chinese_chars": true, |
| "tokenizer_class": "MPNetTokenizer", |
| "unk_token": { |
| "__type": "AddedToken", |
| "content": "[UNK]", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false |
| } |
| } |
|
|
