multilingual_en_uk_pl_ru / tokenizer_config.json
uaritm's picture
Upload 10 files
ffdc8a3
raw
history blame contribute delete
451 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": "xlm-roberta-base",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}