New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Feature] Using NaViT as a Visual Foundation Model #799

Closed

quinwu opened this issue Dec 26, 2024 · 0 comments

quinwu commented Dec 26, 2024

Motivation

The native variable-size ViT seems to work better, as compared in the Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution, has it been considered to introduce NaViT Vision Encoder in InternVL.

Related resources

https://huggingface.co/HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit

Additional context

No response

quinwu closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment