| { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": true, | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "[MASK]", | |
| "max_length": 30, | |
| "model_max_length": 30, | |
| "never_split": null, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "[PAD]", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "[SEP]", | |
| "stride": 0, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "[UNK]" | |
| } | |