updating all configs, adding both fast and legacy tokenizers, also adding tensorflow checkpoint for compatibility
27c33d2
| { | |
| "do_lower_case": true, | |
| "unk_token": "[UNK]", | |
| "sep_token": "[SEP]", | |
| "pad_token": "[PAD]", | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "tokenize_chinese_chars": true, | |
| "strip_accents": false, | |
| "do_basic_tokenize": true, | |
| "never_split": null, | |
| "model_max_length": 512 | |
| } |