vectorizing_model/tokenizer_config.json

{
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<s>",
  "do_lower_case": true,
  "eos_token": "</s>",
  "mask_token": {
    "__type": "AddedToken",
    "content": "<mask>",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 512,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "<unk>"
}