tokenizer_config.json

{
  "backend": "tokenizers",
  "clean_text": false,
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "extra_special_tokens": [
    "[CTX_DAILY]",
    "[CTX_EPIC]",
    "[CTX_LIT]",
    "[CTX_LEGAL]",
    "[CTX_CHURCH]",
    "[CTX_TOROT]",
    "[CTX_BOOK]"
  ],
  "is_local": true,
  "lowercase": false,
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "strip_accents": false,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"
}