Update README.md

README.md

@@ -11,8 +11,6 @@ Code: https://github.com/facebookresearch/eai-vc
 Other Links: VC-1 Website, VC-1 Blogpost, VC-1 Paper, VC-1 Demo
 The VC-1 model is a vision transformer (ViT) pre-trained on over 4,000 hours of egocentric videos from 7 different sources, together with ImageNet. The model is trained using Masked Auto-Encoding (MAE) and is available in two sizes: ViT-B and ViT-L. The model is intended for use for EmbodiedAI tasks, such as object manipulation and indoor navigation.
 The VC-1 model is a vision transformer (ViT) pre-trained on over 4,000 hours of egocentric videos from 7 different sources, together with ImageNet. The model is trained using Masked Auto-Encoding (MAE) and is available in two sizes: ViT-B and ViT-L. The model is intended for use for EmbodiedAI tasks, such as object manipulation and indoor navigation.
-* VC-1 (ViT-L): Our best model, uses a ViT-L backbone, also known simply as `VC-1` | [Download](https://dl.fbaipublicfiles.com/eai-vc/vc1_vitl.pth)
-* VC-1-base (VIT-B): pre-trained on the same data as VC-1 but with a smaller backbone (ViT-B) | [Download](https://dl.fbaipublicfiles.com/eai-vc/vc1_vitb.pth)
 
 ## Model Details