tokenizer_config.json

{
  "add_prefix_space": false,
  "additional_special_tokens": [
    "<|endoftext|>",
    "<fim_prefix>",
    "<fim_middle>",
    "<fim_suffix>",
    "<fim_pad>",
    "<filename>",
    "<gh_stars>",
    "<issue_start>",
    "<issue_comment>",
    "<issue_closed>",
    "<jupyter_start>",
    "<jupyter_text>",
    "<jupyter_code>",
    "<jupyter_output>",
    "<empty_output>",
    "<commit_before>",
    "<commit_msg>",
    "<commit_after>",
    "<reponame>"
  ],
  "bos_token": "<|endoftext|>",
  "eos_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "name_or_path": "/mnt/efs/people/dejiaoz/universal_embedding/codesage_v3/tokenizer/starcoder/",
  "special_tokens_map_file": "/mnt/efs/people/dejiaoz/universal_embedding/codesage_v3/tokenizer/starcoder/special_tokens_map.json",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
}