tokenizer_config.json

{
  "add_prefix_space": false,
  "additional_special_tokens": null,
  "backend": "tokenizers",
  "bos_token": "]~!b[",
  "clean_up_tokenization_spaces": false,
  "eos_token": "[e~[",
  "errors": "replace",
  "extra_special_tokens": [
    "<code_interpreter>",
    "<commit_after>",
    "<commit_before>",
    "<commit_msg>",
    "<empty_output>",
    "<filename>",
    "<fim_middle>",
    "<fim_pad>",
    "<fim_prefix>",
    "<fim_suffix>",
    "<function_call>",
    "<gh_stars>",
    "]<]speech[>[",
    "]<]image[>[",
    "]<]video[>[",
    "]<]start of speech[>[",
    "]<]end of speech[>[",
    "]<]start of image[>[",
    "]<]end of image[>[",
    "]<]start of video[>[",
    "]<]end of video[>[",
    "]<]vision pad[>[",
    "]~!b[",
    "<issue_closed>",
    "<issue_comment>",
    "<issue_start>",
    "<jupyter_code>",
    "<jupyter_output>",
    "<jupyter_start>",
    "<jupyter_text>",
    "<reponame>",
    "[e~[",
    "]!d~[",
    "]!p~[",
    "]~b]",
    "<jupyter_error>",
    "<add_file>",
    "<delete_file>",
    "<rename_file>",
    "<edit_file>",
    "<commit_message>",
    "<empty_source_file>",
    "<repo_struct>",
    "<code_context>",
    "<file_content>",
    "<source_files>",
    "<pr_start>",
    "<review_comment>",
    "<filepath>",
    "<file_sep>"
  ],
  "is_local": true,
  "model_max_length": 40960000,
  "pad_token": null,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "]!d~["
}