tokenizer_config.json

{
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "mask_token": "[MASK]",
  "model_max_length": 128,
  "name_or_path": "KoichiYasuoka/roberta-small-japanese-aozora-char",
  "never_split": [
    "[PAD]",
    "[UNK]",
    "[CLS]",
    "[SEP]",
    "[MASK]"
  ],
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--KoichiYasuoka--roberta-small-japanese-aozora-char/snapshots/dbbd6a003dc65a1876898e3667121ab48265cc94/special_tokens_map.json",
  "strip_accents": false,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"
}