tokenizer_config.json

{
  "cls_token": "<s>",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "mask_token": "<mask>",
  "model_max_length": 416,
  "never_split": null,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "strip_accents": false,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizerFast",
  "unk_token": "<unk>"
}