tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "bos_token": "<s>", |
| 4 | "cls_token": "<s>", |
| 5 | "eos_token": "</s>", |
| 6 | "errors": "replace", |
| 7 | "mask_token": "<mask>", |
| 8 | "model_max_length": 512, |
| 9 | "name_or_path": "roberta-base", |
| 10 | "pad_token": "<pad>", |
| 11 | "sep_token": "</s>", |
| 12 | "special_tokens_map_file": null, |
| 13 | "tokenizer_class": "RobertaTokenizer", |
| 14 | "trim_offsets": true, |
| 15 | "unk_token": "<unk>" |
| 16 | } |
| 17 | |