e5-small-en-ru / tokenizer_config.json
d0rj's picture
fix: tokenizer fix
8937e32
raw
history blame
471 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}