Update README.md

README.md

@@ -1,4 +1,22 @@
 ---
-library_name: transformers
+license: mit
+datasets:
+- ILSVRC/imagenet-1k
+- mlfoundations/datacomp_small
+base_model:
+- laion/CLIP-ViT-H-14-laion2B-s32B-b79K
 ---
-Initialized with RCLIP/OpenCLIP-ViT-H-rho50-k1 and trained with FARE2 for 1 epoch on ImageNet, bs 128
+
+Model Initialized from `laion/CLIP-ViT-H-14-laion2B-s32B-b79K`. The image encoder is finetuned with FARE at $\epsilon=2/255$. The text encoder is finetuned with LEAF at $k=1$ with $\rho=50$.
+
+To load this model use:
+
+```python
+from transformers import CLIPProcessor, CLIPModel
+
+model_name = "LEAF-CLIP/OpenCLIP-ViT-H-rho50-k1-FARE2"
+processor_name = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K"
+
+model = CLIPModel.from_pretrained(model_name)
+processor = CLIPProcessor.from_pretrained(processor_name)
+```