Fix resolution in Preprocessing subsection

README.md

@@ -86,7 +86,7 @@ SigLIP is pre-trained on the WebLI dataset [(Chen et al., 2023)](https://arxiv.o
 
 ### Preprocessing
 
-Images are resized/rescaled to the same resolution (384x384) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).
+Images are resized/rescaled to the same resolution (224x224) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).
 
 Texts are tokenized and padded to the same length (64 tokens).