34 lines
762 B
JSON
34 lines
762 B
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>",
|
|
"<jupyter_script>",
|
|
"<empty_output>"
|
|
],
|
|
"is_local": false,
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": null,
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|endoftext|>",
|
|
"vocab_size": 49152
|
|
}
|