tokenizer-the-stack-march-sample / tokenizer_config.json
cakiki's picture
Upload tokenizer
2e704d2
{
"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>"
],
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}