BertTokenizer(
  name_or_path='bert-base-uncased',
  vocab_size=30522,
  model_max_length=512,
  is_fast=False,
  padding_side='right',
  truncation_side='right',
  special_tokens={
    'unk_token': '[UNK]',
    'sep_token': '[SEP]',
    'pad_token': '[PAD]',
    'cls_token': '[CLS]',
    'mask_token': '[MASK]'},
  clean_up_tokenization_spaces=True),

added_tokens_decoder={
  0: AddedToken(
    "[PAD]",
    rstrip=False,
    lstrip=False,
    single_word=False,
    normalized=False,  
    special=True),

  100: AddedToken(
    "[UNK]",
    rstrip=False,
    lstrip=False,
    single_word=False,
    normalized=False,
    special=True),

  101: AddedToken(
    "[CLS]",
    rstrip=False,
    lstrip=False,
    single_word=False,
    normalized=False,
    special=True),

  102: AddedToken(
    "[SEP]",
    rstrip=False,
    lstrip=False,
    single_word=False,
    normalized=False,
    special=True),

  103: AddedToken(
    "[MASK]",
    rstrip=False,
    lstrip=False,
    single_word=False,
    normalized=False,
    special=True),
  }