| { |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "0": { |
| "content": "[PAD]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "11": { |
| "content": "[UNK]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "12": { |
| "content": "[CLS]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "13": { |
| "content": "[SEP]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "14": { |
| "content": "[MASK]", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "591": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "592": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": true, |
| "cls_token": "[CLS]", |
| "eos_token": "</s>", |
| "errors": "replace", |
| "full_tokenizer_file": null, |
| "mask_token": "[MASK]", |
| "max_len": 512, |
| "model_max_length": 512, |
| "pad_token": "[PAD]", |
| "sep_token": "[SEP]", |
| "tokenizer_class": "RobertaTokenizer", |
| "trim_offsets": true, |
| "unk_token": "[UNK]" |
| } |
|
|
