nllb-tatoeba-gos-nld-v1 / tokenizer_config.json
Tom9358's picture
Upload tokenizer
1dfb0a1 verified
Raw
History Blame
651 Bytes
{
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"extra_special_tokens": [
"gos_Latn"
],
"is_local": true,
"legacy_behaviour": false,
"mask_token": "<mask>",
"max_length": 43,
"model_max_length": 1024,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "</s>",
"sp_model_kwargs": {},
"src_lang": "nld_Latn",
"stride": 0,
"tgt_lang": "gos_Latn",
"tokenizer_class": "NllbTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}