| [DocVQA Task1](https://rrc.cvc.uab.es/?ch=17)(Document VQA) | 0.78 | 67.5 | [donut-base-finetuned-docvqa](https://huggingface.co/naver-clova-ix/donut-base-finetuned-docvqa/tree/official) | [gradio space web demo](https://huggingface.co/spaces/nielsr/donut-docvqa),<br>[google colab demo](https://colab.research.google.com/drive/1Z4WG8Wunj3HE0CERjt608ALSgSzRC9ig?usp=sharing) |
The links to the pre-trained backbones are here:
The links to the pre-trained backbones are here:
-[`donut-base`](https://huggingface.co/naver-clova-ix/donut-base/tree/official): trained with 64 A100 GPUs (~2.5 days), number of layers (encoder: {2,2,14,2}, decoder: 4), input size 2560x1920, swin window size 10, IIT-CDIP (11M) and SynthDoG (ECJK, 0.5M x 4).
-[`donut-base`](https://huggingface.co/naver-clova-ix/donut-base/tree/official): trained with 64 A100 GPUs (~2.5 days), number of layers (encoder: {2,2,14,2}, decoder: 4), input size 2560x1920, swin window size 10, IIT-CDIP (11M) and SynthDoG (ECJK, 0.5M x 4).
...
@@ -61,6 +61,7 @@ To generate synthetic datasets with our SynthDoG, please see `./synthdog/README.
...
@@ -61,6 +61,7 @@ To generate synthetic datasets with our SynthDoG, please see `./synthdog/README.
## Updates
## Updates
**_2022-08-12_** Donut 🍩 is also available at [huggingface/transformers 🤗](https://huggingface.co/docs/transformers/main/en/model_doc/donut)(contributed by [@NielsRogge](https://github.com/NielsRogge)).<br>
**_2022-07-20_** First Commit, We release our code, model weights, synthetic data and generator.
**_2022-07-20_** First Commit, We release our code, model weights, synthetic data and generator.
