Add library name and pipeline tag

This PR improves the model card by adding the `library_name` (Transformers) and the correct pipeline tag, so that the model can be found at https://huggingface.co/models?pipeline_tag=feature-extraction.

README.md

@@ -1,11 +1,14 @@
 ---
-license: mit
+base_model:
+- openai/clip-vit-large-patch14
 datasets:
 - ILSVRC/imagenet-1k
 - mlfoundations/datacomp_small
-base_model:
-- openai/clip-vit-large-patch14
+license: mit
+library_name: transformers
+pipeline_tag: feature-extraction
 ---
+
 [[Paper]](https://www.arxiv.org/abs/2506.03355)   [[Code]](https://github.com/LIONS-EPFL/LEAF)
 
 Model Initialized from `openai/clip-vit-large-patch14`. The image encoder is finetuned with FARE at $\epsilon=2/255$. The text encoder is finetuned with LEAF at $k=1$ with $\rho=50$ and semantic constraints.
@@ -20,5 +23,4 @@ processor_name = "openai/clip-vit-large-patch14"
 
 model = CLIPModel.from_pretrained(model_name)
 processor = CLIPProcessor.from_pretrained(processor_name)
-```
-
+```