tokenizer_config.json

{
  "tokenizer_class": "CENOCharLevelTokenizer",
  "vocab_size": 512,
  "eos_token": "<eos>",
  "pad_token": "<pad>",
  "unk_token": "<unk>",
  "eod_id": 0,
  "eos_id": 0,
  "pad_id": 1,
  "model_max_length": 1000000000000000019884624838656,
  "clean_up_tokenization_spaces": true,
  "tokenize_chinese_chars": false,
  "strip_accents": null,
  "do_lower_case": false,
  "do_basic_tokenize": false,
  "never_split": null,
  "tokenizer_type": "CharLevelTokenizer",
  "name_or_path": "./ceno_tokenizer",
  "auto_map": {
    "AutoTokenizer": [
      "ceno_tokenizer.CENOCharLevelTokenizer",
      null
    ]
  }
}