just remove PreNorm wrapper from all ViTs, as it is unlikely to change at this point

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '1.4.4',
+  version = '1.4.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   long_description_content_type = 'text/markdown',

vit_pytorch/vit_for_small_dataset.py

@@ -17,7 +17,7 @@ class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
-            nn.LayerNorm(dim),
+            nn.LayerNorm(dim)
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),