autotrain-mbart-dia-55472129249 / tokenizer_config.json
system's picture
system HF staff
Commit From AutoTrain
6586570
raw
history blame contribute delete
522 Bytes
{
"additional_special_tokens": null,
"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": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"src_lang": "en_XX",
"tgt_lang": "ru_RU",
"tokenizer_class": "MBartTokenizer",
"unk_token": "<unk>"
}