dof-Rai2-1 / tokenizer_config.json
Sebabrata's picture
End of training
602daa6
raw
history blame contribute delete
497 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "naver-clova-ix/donut-base",
"pad_token": "<pad>",
"processor_class": "DonutProcessor",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}