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)→
More from Research
- Claude completes 13M-line Lean formalization of Fermat's Last Theorem, largest proof ever — burny_tech · 2026-09-06
- Single-metric robustness claims for LLMs can mislead, multi-level arXiv study finds — burny_tech · 2026-09-06
- Prove2Me: the Lean crowdsourcing platform behind Anthropic's Fermat's Last Theorem formalization — burny_tech · 2026-09-06
- Causal Foundation Models: pretrained nets estimate treatment effects in-context, no retraining — burny_tech · 2026-09-06
- Google and HHMI release largest cellular brain map: complete fly CNS with 166,000 neurons — udmrzn · 2026-09-06
- Unreal Engine pipeline yields 8.7K+ hours of action-conditioned video for world-model pretraining — udmrzn · 2026-09-06