nllb-200-distilled-600M-73K-en-to-dz / tokenizer_config.json
KarmaCST's picture
Training in progress, step 500
56391bf
raw
history blame
556 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": "eng_Latn",
"tgt_lang": "dzo_Tibt",
"tokenizer_class": "NllbTokenizer",
"unk_token": "<unk>"
}