Humayoun
/

ThesisDonutOPD2

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

ThesisDonutOPD2 / .gitignore

Humayoun's picture

Training in progress, epoch 1

8736d81 almost 2 years ago

history blame contribute delete

13 Bytes

checkpoint-*/