donut icon indicating copy to clipboard operation
donut copied to clipboard

Published 20 hours ago • verified publisher icon clovaai

VisionEncoderDecoderModel convert

Open sjtu-cz opened this issue 1 year ago • 2 comments

How to convert the trained donut model into the model structure of VisionEncoderDecoderModel?

sjtu-cz avatar Jan 25 '24 08:01 sjtu-cz

Smells like an xy-problem, what exactly are you trying to do? Importing a donut model with the huggingface VisionEncoderDecoder implementation should be straight forward. Just make sure you use the right DonutTokenizer with it. The docs should cover what you are looking for: https://huggingface.co/docs/transformers/model_doc/donut

felixvor avatar Feb 21 '24 10:02 felixvor

您好，你的邮件我已经收到~

sjtu-cz avatar Feb 21 '24 10:02 sjtu-cz