Update README.md

README.md

@@ -7,14 +7,14 @@ base_model:
 - laion/CLIP-ViT-g-14-laion2B-s34B-b88K
 ---
 
-Model Initialized from `laion/CLIP-ViT-g-14-laion2B-s34B-b88K`. The image encoder is finetuned with FARE at $\epsilon=2/255$.
+Model Initialized from `laion/CLIP-ViT-g-14-laion2B-s12B-b42K`. The image encoder is finetuned with FARE at $\epsilon=2/255$.
 To load this model use:
 
 ```python
 from transformers import CLIPProcessor, CLIPModel
 
 model_name = "LEAF-CLIP/OpenCLIP-ViT-g-FARE2"
-processor_name = "laion/CLIP-ViT-g-14-laion2B-s34B-b88K"
+processor_name = "laion/CLIP-ViT-g-14-laion2B-s12B-b42K"
 
 model = CLIPModel.from_pretrained(model_name)
 processor = CLIPProcessor.from_pretrained(processor_name)