Add ThinkingViT weights

README.md

@@ -15,9 +15,9 @@ metrics:
 - accuracy
 ---
 
-# ThinkingViT 800 Epochs DeiT 3H -> 6H ImageNet-1K
+# ThinkingViT DeiT 3H -> 6H 800 Epochs ImageNet-1K
 
-This repository contains the ImageNet-1K EMA weights for **ThinkingViT 800 Epochs DeiT 3H -> 6H ImageNet-1K** from
+This repository contains the ImageNet-1K EMA weights for **ThinkingViT DeiT 3H -> 6H 800 Epochs ImageNet-1K** from
 [ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference](https://arxiv.org/abs/2507.10800).
 
 - Paper: https://arxiv.org/abs/2507.10800
@@ -34,7 +34,7 @@ import torch
 from timm.models import create_model
 
 # Run from the ThinkingViT repository root, or put this repository on PYTHONPATH.
-model = create_model("hf-hub:NCPS/thinkingvit_800epochs", pretrained=True)
+model = create_model("hf-hub:NCPS/thinkingvit_deit-3h-6h-800epochs-imagenet1k", pretrained=True)
 model.eval()
 
 x = torch.randn(1, 3, 224, 224)