nllb-200-ko-grammarly-600M / tokenizer_config.json
esunn's picture
Upload folder using huggingface_hub
a85a3e3 verified
raw
history blame contribute delete
735 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
},
"max_length": 128,
"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": null,
"stride": 0,
"tgt_lang": null,
"tokenizer_class": "NllbTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}