tokenizer_config.json

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "model_type": "bpe",
  "bos_token": "<|bos|>",
  "eos_token": "<|endoftext|>",
  "pad_token": "<pad>",
  "unk_token": null,
  "clean_up_tokenization_spaces": false,
  "model_max_length": 131072,
  "added_tokens_decoder": {
    "0": {"content": "<pad>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
    "1": {"content": "<|bos|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
    "2": {"content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}
  }
}