tokenizer_config.json

{
    "added_tokens_decoder": {
      "256": {
        "content": "[CLS]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "257": {
        "content": "[SEP]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "258": {
        "content": "[BOW]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "259": {
        "content": "[EOW]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "260": {
        "content": "[PAD]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "261": {
        "content": "[MASK]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      }
    },
    "additional_special_tokens": [
      "[BOW]",
      "[EOW]"
    ],
    "clean_up_tokenization_spaces": true,
    "do_basic_tokenize": true,
    "do_lower_case": true,
    "cls_token": "[CLS]",
    "sep_token": "[SEP]",
    "mask_token": "[MASK]",
    "pad_token": "[PAD]",
    "max_word_length": 50,
    "model_max_length": 512,
    "never_split": null,
    "strip_accents": null,
    "tokenize_chinese_chars": true,
    "tokenizer_class": "CharacterBertTokenizer"
  }