Downloads · 30 days
16
2% of all-time downloads
donut-base-ascii
nbroad/donut-base-ascii
donut-base-ascii is a image-text-to-text model from nbroad. 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 apache-2.0.
This is "naver-clova-ix/donut-base" but with all non-ascii tokens removed. This means the model is good for basic English use cases where the text is primarily a-zA-Z0-9 and basic punctuation.
All-time downloads
791
Public
Repo size
2.1 GB
Likes
7
Public
Repo makeup
Click a slice to open those files.
.bin686 MB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Aug 1, 2023
- Updated
- Aug 14, 2023
- SHA
- 39129e81
Try a prompt
Model card
From the Hugging Face model README
donut-base-ascii
This is "naver-clova-ix/donut-base" but with all non-ascii tokens removed. This means the model is good for basic English use cases where the text is primarily a-zA-Z0-9 and basic punctuation.
The original model, "naver-clova-ix/donut-base", did not have a token for "1", so that has also been added. The notebook remove-donut-tokens.ipynb details the whole process.
This has not been trained any more than the original model.
I made a whole video about it: https://youtu.be/Uzr553x1gdM
I did a quick speed test for generation against the default model and using bad_words_ids. The bad_words_ids was only 12k tokens instead of the 30k that were removed and it was still noticeably slower.
Speed script here
Launched with this
approach | time to generate 10 tokens
- | -
"naver-clova-ix/donut-base" | 205ms
"naver-clova-ix/donut-base" + 12k
bad_words_ids| 280ms "donut-base-ascii" | 195ms
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- apache-2.0
- Created
- Aug 1, 2023
- Updated
- Aug 14, 2023