tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "is_local": false,
  "local_files_only": false,
  "lowercase": false,
  "model_max_length": 2048,
  "pad_token": "</s>",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "[UNK]",
  "vocab_size": 12000
}