nllb-rus-tyv-v2-extvoc / tokenizer_config.json
cointegrated's picture
Upload tokenizer
c70f010
raw
history blame contribute delete
570 Bytes
{
"additional_special_tokens": null,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"legacy_behaviour": false,
"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": null,
"tgt_lang": null,
"tokenizer_class": "NllbTokenizer",
"tokenizer_file": null,
"unk_token": "<unk>"
}