sbert-base-ja-arc / tokenizer_config.json
LeoChiuu's picture
Add new SentenceTransformer model.
e21f71e verified
raw
history blame
386 Bytes
{
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"split_by_punct": false,
"tokenizer_class": "DebertaV2Tokenizer",
"unk_token": "<unk>"
}