Medxa
/

donut-paper-ktp

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

donut-paper-ktp

815 MB

1 contributor

History: 360 commits

aryaadhi's picture

Best model with eval_loss 0.4990

5fd4a18 verified 7 months ago