tokenizer_config.json

{
  "add_prefix_space": false,
  "backend": "tokenizers",
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "extra_special_tokens": [
    "<|endoftext|>",
    "<|im_start|>",
    "<|im_end|>",
    "<repo_name>",
    "<reponame>",
    "<file_sep>",
    "<filename>",
    "<gh_stars>",
    "<issue_start>",
    "<issue_comment>",
    "<issue_closed>",
    "<jupyter_start>",
    "<jupyter_text>",
    "<jupyter_code>",
    "<jupyter_output>",
    "<|sep|>",
    "<|mask|>"
  ],
  "mask_token": "<|mask|>",
  "model_max_length": 32768,
  "pad_token": "<|endoftext|>",
  "sep_token": "<|sep|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
}