tokenizer_config.json
| 1 | { |
| 2 | "bos_token": "[CLS]", |
| 3 | "cls_token": "[CLS]", |
| 4 | "do_lower_case": false, |
| 5 | "eos_token": "[SEP]", |
| 6 | "mask_token": "[MASK]", |
| 7 | "model_max_length": 512, |
| 8 | "name_or_path": "./nli-scratch/best-multilingual-26lang-2mil7/best-multilingual-nli", |
| 9 | "pad_token": "[PAD]", |
| 10 | "sep_token": "[SEP]", |
| 11 | "sp_model_kwargs": {}, |
| 12 | "special_tokens_map_file": null, |
| 13 | "split_by_punct": false, |
| 14 | "tokenizer_class": "DebertaV2Tokenizer", |
| 15 | "unk_token": "[UNK]", |
| 16 | "vocab_type": "spm" |
| 17 | } |
| 18 | |