tokenizer_config.json

{
  "add_prefix_space": true,
  "additional_special_tokens": [
    "[R-0]",
    "[R-1]",
    "[R-2]",
    "[R-3]",
    "[R-4]",
    "[R-5]",
    "[R-6]",
    "[R-7]",
    "[R-8]",
    "[R-9]",
    "[R-10]",
    "[R-11]",
    "[R-12]",
    "[R-13]",
    "[R-14]",
    "[R-15]",
    "[R-16]",
    "[R-17]",
    "[R-18]",
    "[R-19]",
    "--NME--",
    "[E-0]",
    "[E-1]",
    "[E-2]",
    "[E-3]",
    "[E-4]",
    "[E-5]",
    "[E-6]",
    "[E-7]",
    "[E-8]",
    "[E-9]",
    "[E-10]",
    "[E-11]",
    "[E-12]",
    "[E-13]",
    "[E-14]",
    "[E-15]",
    "[E-16]",
    "[E-17]",
    "[E-18]",
    "[E-19]",
    "[E-20]",
    "[E-21]",
    "[E-22]",
    "[E-23]",
    "[E-24]"
  ],
  "bos_token": "[CLS]",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "sp_model_kwargs": {},
  "split_by_punct": false,
  "tokenizer_class": "DebertaV2Tokenizer",
  "unk_token": "[UNK]",
  "vocab_type": "spm"
}