tokenizer_config.json

{
  "add_prefix_space": true,
  "backend": "tokenizers",
  "bos_token": "[CLS]",
  "cls_token": "[CLS]",
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "extra_special_tokens": [
    "[START]",
    "[END]",
    "[GLOSS]"
  ],
  "is_local": false,
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "split_by_punct": false,
  "tokenizer_class": "DebertaV2Tokenizer",
  "unk_id": 3,
  "unk_token": "[UNK]",
  "vocab_type": "spm"
}