nllb-mulgi / tokenizer_config.json
remots's picture
Training in progress, epoch 1
b480f00 verified
Raw
History Blame Contribute Delete
458 Bytes
{
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"extra_special_tokens": [
"mul_Latn"
],
"is_local": false,
"legacy_behaviour": false,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"src_lang": "eng_Latn",
"tgt_lang": null,
"tokenizer_class": "NllbTokenizer",
"unk_token": "<unk>"
}