update arxiv link

timm/models/vision_transformer_hybrid.py

@@ -6,7 +6,7 @@ A PyTorch implement of the Hybrid Vision Transformers as described in:
     - https://arxiv.org/abs/2010.11929
 
 `How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers`
-    - https://arxiv.org/abs/2106.TODO
+    - https://arxiv.org/abs/2106.10270
 
 NOTE These hybrid model definitions depend on code in vision_transformer.py.
 They were moved here to keep file sizes sane.
@@ -360,4 +360,4 @@ def vit_base_resnet50d_224(pretrained=False, **kwargs):
     model_kwargs = dict(embed_dim=768, depth=12, num_heads=12, **kwargs)
     model = _create_vision_transformer_hybrid(
         'vit_base_resnet50d_224', backbone=backbone, pretrained=pretrained, **model_kwargs)
-    return model
+    return model