tokenizer_config.json

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "vocab_size": 49152,
  "model_max_length": 8192,
  "pad_token": "<pad>",
  "bos_token": "<bos>",
  "eos_token": "<eos>",
  "unk_token": "<unk>",
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "unk_token_id": 3,
  "add_bos_token": false,
  "add_eos_token": false,
  "clean_up_tokenization_spaces": true,
  "split_special_tokens": false
}