NaFlexViT CLIP test model (dual jitter) now on Hugging Face

wightmanr · x · 2026-09-06

This is the Hugging Face link for rwightman's previously announced experimental model: rwightman/naflexViT-B-32.cc12m-pj24-32-40, an OpenCLIP ViT-B-32 trained on pixparse/cc12m-wds for zero-shot image classification, Apache-2.0 licensed. It was trained with both FlexiViT patch size jitter and NaFlex-style sequence length jitter; see the original post for details.

Related event: timm Author Releases NaFlexViT CLIP Model with Dual Jitter(2 posts)→

Original post →

More from Research

Research channel →