Update README.md

README.md

@@ -4,9 +4,11 @@ datasets:
 - ILSVRC/imagenet-1k
 ---
 
-# Vision Transformer (large-sized model) trained using DINOv2 on ImageNet-1K only
+# Vision Transformer (ViT) trained using DINOv2 on ImageNet-1K only
 
-Reproduction of the ViT-L/16 results from the [DINOv2 repo](https://github.com/facebookresearch/dinov2/blob/main/dinov2/configs/train/vitl16_short.yaml)
+Reproduction of the ViT-L/16 results from the [DINOv2 repo](https://github.com/facebookresearch/dinov2/blob/main/dinov2/configs/train/vitl16_short.yaml) (which uses only ImageNet-1K in 224x224 resolution).
+
+The [original](https://huggingface.co/facebook/dinov2-large) work uses the much larger LVD142M dataset and distills a larger model (g/14) into a L/14 model.
 
 ### How to use