tokenizer_config.json

{
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "full_tokenizer_file": null,
  "mask_token": "[MASK]",
  "max_length": 384,
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": "[SEP]",
  "stride": 128,
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "DistilBertTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "only_second",
  "unk_token": "[UNK]"
}