tokenizer_config.json

{
  "added_tokens": [
    {
      "content": "[PAD]",
      "id": 0,
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    {
      "content": "[UNK]",
      "id": 1,
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    {
      "content": "[CLS]",
      "id": 2,
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    {
      "content": "[SEP]",
      "id": 3,
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    {
      "content": "[MASK]",
      "id": 4,
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  ],
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "extra_special_tokens": {},
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "normalizer": {
    "clean_text": true,
    "handle_chinese_chars": true,
    "lowercase": false,
    "strip_accents": null,
    "type": "BertNormalizer"
  },
  "pad_token": "[PAD]",
  "padding": null,
  "post_processor": null,
  "pre_tokenizer": {
    "type": "BertPreTokenizer"
  },
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "truncation": null,
  "unk_token": "[UNK]",
  "version": "1.0"
}