custom-decoder-ats / tokenizer_config.json
josh-oo's picture
Added modified mBART tokenizer
7f1c756
{
"additional_special_tokens": null,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"src_lang": null,
"tgt_lang": null,
"tokenizer_class": "MBartTokenizer",
"tokenizer_file": null,
"unk_token": "<unk>"
}