Seb-AI-S1-Mini-Instruct / tokenizer_config.json
Sebestianmek's picture
End of training
fae6b42 verified
Raw History Blame Contribute Delete
910 Bytes
{
"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,
"local_files_only": false,
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}