laion
/

CLIP-convnext_large_d.laion2B-s26B-b102K-augreg

Zero-Shot Image Classification

Model card Files Files and versions

Metrics Training metrics Community

rwightman HF Staff commited on Jan 29, 2023

Commit

70081e2

·

1 Parent(s): d081641

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -128,7 +128,7 @@ The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/ab
 The models achieve between 75.9 top-1 zero-shot accuracy on ImageNet-1k.
-![](convnext_base_w_zero_shot.png)
 An initial round of benchmarks have been performed on a wider range of datasets, to be viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
@@ -136,7 +136,7 @@ As part of exploring increased augmentation + regularization, early evalations s
 # Acknowledgements
-Acknowledging [stability.ai](https://stability.ai/) and the Gauss Centre for Supercomputing e.V. (http://gauss-centre.eu) for funding this part of work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC).
 # Citation

 The models achieve between 75.9 top-1 zero-shot accuracy on ImageNet-1k.
+![](convnext_large_d_zero_shot.png)
 An initial round of benchmarks have been performed on a wider range of datasets, to be viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
 # Acknowledgements
+Acknowledging [stability.ai](https://stability.ai/) for compute used to train this model.
 # Citation