chinese-roberta-wwm-ext / tokenizer_config.json
tuhailong's picture
first commit
857ade4
raw
history blame
351 Bytes
{"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": null, "special_tokens_map_file": "./chinese-roberta-wwm-ext/special_tokens_map.json", "name_or_path": "./chinese-roberta-wwm-ext", "tokenizer_class": "BertTokenizer"}