diff --git a/timm/models/vision_transformer.py b/timm/models/vision_transformer.py
index acd4d18d..448ef1e6 100644
--- a/timm/models/vision_transformer.py
+++ b/timm/models/vision_transformer.py
@@ -488,7 +488,7 @@ def _create_vision_transformer(variant, pretrained=False, distilled=False, **kwa
 
 @register_model
 def vit_small_patch16_224(pretrained=False, **kwargs):
-    """ My custom 'small' ViT model. Depth=8, heads=8= mlp_ratio=3."""
+    """ My custom 'small' ViT model. Depth=8, heads=8, mlp_ratio=3."""
     model_kwargs = dict(
         patch_size=16, embed_dim=768, depth=8, num_heads=8, mlp_ratio=3.,
         qkv_bias=False, norm_layer=nn.LayerNorm, **kwargs)
@@ -784,4 +784,4 @@ def vit_deit_base_distilled_patch16_384(pretrained=False, **kwargs):
     model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
     model = _create_vision_transformer(
         'vit_deit_base_distilled_patch16_384', pretrained=pretrained, distilled=True, **model_kwargs)
-    return model
\ No newline at end of file
+    return model