starcoderbase-1b-sft / tokenizer_config.json
abacaj's picture
Upload tokenizer
36a4249
{
"add_bos_token": false,
"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": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 2048,
"pad_token": {
"__type": "AddedToken",
"content": "<|pad|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"vocab_size": 49152
}