data/indus_tokenizer/tokenizer_config.json

{
  "backend": "tokenizers",
  "cls_token": "[CLS]",
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "[UNK]"
}