Downloads · 30 days
95
2% of all-time downloads
donut-demo
nielsr/donut-demo
donut-demo is a image-text-to-text model from nielsr. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
This model is the result of fine-tuning VisionEncoderDecoderModel on the naver-clova-ix/cord-v2 dataset.
All-time downloads
4.2K
Public
Parameters
202M
222 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin809 MB · 50%
Parameter types
How the weights are stored.
F32202M · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
Donut demo
This model is the result of fine-tuning VisionEncoderDecoderModel on the naver-clova-ix/cord-v2 dataset.
The Weights and Biases report can be found here.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Aug 15, 2022
- Updated
- Nov 23, 2024