tokenizer_config.json

{"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, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "basic", "subword_tokenizer_type": "character", "never_split": ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]"], "mecab_kwargs": null, "do_basic_tokenize": true, "tokenizer_class": "BertTokenizer"}