data/indus_tokenizer/tokenizer_info.json

{
  "vocab_size": 646,
  "indus_token_count": 641,
  "pad_token_id": 0,
  "cls_token_id": 2,
  "sep_token_id": 3,
  "mask_token_id": 4,
  "unk_token_id": 1
}