multilingual_en_ru_uk / tokenizer_config.json
uaritm's picture
Add new SentenceTransformer model.
2f8c59d
raw
history blame
513 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "/content/drive/MyDrive/AI_Project/embed/make-multilingual-en-ru-uk-2022-07-04/",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}