m2m100_418M_ft_ru-kbd_44K / tokenizer_config.json
anzorq's picture
add tokenizer
fa5cb88
raw
history blame
564 Bytes
{
"additional_special_tokens": null,
"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": 1024,
"name_or_path": "facebook/nllb-200-distilled-600M",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"src_lang": "ru",
"tgt_lang": "zu",
"tokenizer_class": "NllbTokenizer",
"unk_token": "<unk>"
}