tokenizer_config.json

{
    "clean_up_tokenization_spaces": true,
    "cls_token": "[CLS]",
    "do_basic_tokenize": true,
    "do_lower_case": true,
    "mask_token": "[MASK]",
    "max_len": 512,
    "model_max_length": 512,
    "never_split": null,
    "pad_token": "[PAD]",
    "sep_token": "[SEP]",
    "strip_accents": null,
    "tokenize_chinese_chars": true,
    "tokenizer_class": "BertTokenizer",
    "unk_token": "[UNK]"
  }