diff --git a/timm/models/vision_transformer.py b/timm/models/vision_transformer.py
index 02c32cb7..f6a09ac2 100644
--- a/timm/models/vision_transformer.py
+++ b/timm/models/vision_transformer.py
@@ -541,7 +541,11 @@ 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. embed_dim=768, depth=8, num_heads=8, mlp_ratio=3.
+    NOTE:
+        * this differs from the DeiT based 'small' definitions with embed_dim=384, depth=12, num_heads=6
+        * this model does not have a bias for QKV (unlike the official ViT and DeiT models)
+    """
     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)
@@ -994,4 +998,4 @@ 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