alpaca-guanaco-japanese-gpt-1b / tokenizer_config.json
inu-ai's picture
Upload tokenizer
c35b6d1
raw
history blame
405 Bytes
{
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}