Fix latents shape in snippet output

README.md

@@ -118,7 +118,7 @@ We will use [`einops`](https://einops.rocks/) (install with `pip install einops`
 >>> flat_patch_embeddings = outputs.last_hidden_state[:, 1:]  # first token is CLS
 >>> reshaped_patch_embeddings = reshape_patch_embeddings(flat_patch_embeddings)
 >>> reshaped_patch_embeddings.shape  # (batch_size, num_channels, height, width)
-torch.Size([1, 768, 16, 16])
+torch.Size([1, 768, 37, 37])
 ```
 
 ## Training details