tokenizer_config.json

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "model_max_length": 1024,
  "padding_side": "right",
  "truncation_side": "right",
  "pad_token": "[PAD]",
  "unk_token": "[UNK]",
  "cls_token": "[CLS]",
  "sep_token": "[SEP]",
  "mask_token": "[MASK]",
  "clean_up_tokenization_spaces": false,
  "added_tokens_decoder": {
    "2": {
      "content": "[PAD]",
      "lstrip": false,
      "rstrip": false,
      "single_word": false,
      "normalized": false,
      "special": true
    },
    "3": {
      "content": "[UNK]",
      "lstrip": false,
      "rstrip": false,
      "single_word": false,
      "normalized": false,
      "special": true
    },
    "4": {
      "content": "[CLS]",
      "lstrip": false,
      "rstrip": false,
      "single_word": false,
      "normalized": false,
      "special": true
    },
    "5": {
      "content": "[SEP]",
      "lstrip": false,
      "rstrip": false,
      "single_word": false,
      "normalized": false,
      "special": true
    },
    "6": {
      "content": "[MASK]",
      "lstrip": false,
      "rstrip": false,
      "single_word": false,
      "normalized": false,
      "special": true
    }
  }
}