roberta-base-chinese-extractive-qa / tokenizer_config.json

First version of the roberta-base-chinese-extractive-qa model and tokenizer.

9c7aa1e almost 4 years ago

216 Bytes

{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512}