a7a1fb8a83
- update(tokenizer): convert to `GPT2Tokenizer` (85625532dc8753c206eecc8a76323783a7b64744)
40 lines
784 B
JSON
40 lines
784 B
JSON
{
|
|
"additional_special_tokens": [
|
|
"<|reg_extra|>",
|
|
"<|endoftext|>",
|
|
"<|fim_prefix|>",
|
|
"<|fim_middle|>",
|
|
"<|fim_suffix|>",
|
|
"<|fim_pad|>",
|
|
"<gh_stars>",
|
|
"<filename>",
|
|
"<issue_start>",
|
|
"<issue_comment>",
|
|
"<issue_closed>",
|
|
"<jupyter_start>",
|
|
"<jupyter_text>",
|
|
"<jupyter_code>",
|
|
"<jupyter_output>",
|
|
"<empty_output>",
|
|
"<commit_before>",
|
|
"<commit_msg>",
|
|
"<commit_after>",
|
|
"<reponame>",
|
|
"<|endofprompt|>",
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|pause|>",
|
|
"<|reg0|>",
|
|
"<|reg1|>",
|
|
"<|reg2|>",
|
|
"<|reg3|>",
|
|
"<|reg4|>",
|
|
"<|reg5|>",
|
|
"<|reg6|>",
|
|
"<|reg7|>",
|
|
"<|extra0|>"
|
|
],
|
|
"bos_token": "<|endoftext|>",
|
|
"eos_token": "<|endoftext|>",
|
|
"unk_token": "<|endoftext|>"
|
|
} |