| { |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "30000": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "30001": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "30002": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "30003": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "30004": { |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": false, |
| "cls_token": "<s>", |
| "eos_token": "</s>", |
| "errors": "replace", |
| "extra_special_tokens": {}, |
| "mask_token": "<mask>", |
| "max_length": 256, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "<pad>", |
| "sep_token": "</s>", |
| "stride": 0, |
| "tokenizer_class": "RobertaTokenizer", |
| "trim_offsets": true, |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": "<unk>" |
| } |
|
|
