E5SmallDistilV2 / tokenizer_config.json
potanin-marat's picture
Tokenizer from multilingual-e5-small
a1ba064 verified
raw
history blame contribute delete
349 Bytes
{
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"is_local": false,
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}