Muennighoff/vilio

🥶Vilio: State-of-the-art VL models in PyTorch & PaddlePaddle

45
/ 100
Emerging

Vilio helps researchers and machine learning engineers analyze how images and text interact, particularly for tasks like detecting harmful content. You provide it with multimodal data (images with associated text, like memes), and it outputs predictions or classifications based on advanced vision-language models. It's designed for those working with cutting-edge AI for content understanding.

No commits in the last 6 months.

Use this if you are a researcher or ML engineer developing or evaluating state-of-the-art vision-language models for tasks that combine image and text understanding.

Not ideal if you need a simple, off-the-shelf tool for basic image or text analysis without deep dives into model architectures or multimodal learning.

Multimodal AI Content Moderation Deep Learning Research Natural Language Processing Computer Vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

91

Forks

28

Language

Python

License

MIT

Last pushed

Jun 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Muennighoff/vilio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.