Improve model card: add metadata, paper, project & code links

This PR enhances the model card by:
- Adding `pipeline_tag: zero-shot-image-classification` to enable discovery on the Hub and activate the inference widget.
- Adding `library_name: open_clip` to provide a ready-to-use code snippet.
- Specifying `license: apache-2.0`.
- Including a link to the paper: [Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning](https://huggingface.co/papers/2505.24424).
- Adding a link to the project page: [https://clic-compositional-clip.github.io/](https://clic-compositional-clip.github.io/).
- Adding a link to the GitHub repository: [https://github.com/AmitPeleg/CLIC](https://github.com/AmitPeleg/CLIC).
- Correcting the sample usage snippet by adding `from urllib.request import urlopen`.

These additions will make the model more discoverable and provide users with comprehensive information.

README.md

@@ -1,6 +1,15 @@
+---
+license: apache-2.0
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+---
 
 # Model Card for CLIC-ViT-B-32-224-CogVLM
 
+This model is presented in the paper [Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning](https://huggingface.co/papers/2505.24424).
+Project Page: [https://clic-compositional-clip.github.io/](https://clic-compositional-clip.github.io/)
+Code: [https://github.com/AmitPeleg/CLIC](https://github.com/AmitPeleg/CLIC)
+
 ## Model Details
 
 <!-- Provide the basic links for the model. -->
@@ -10,10 +19,12 @@
 ## Model Usage
 ### With OpenCLIP
 
-```
+```python
 import torch
 from PIL import Image
 import open_clip
+from urllib.request import urlopen
+
 
 model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:nmndeep/CLIC-ViT-B-32-224-CogVLM')
 
@@ -38,5 +49,5 @@ with torch.no_grad(), torch.autocast("cuda"):
 
     text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
 idx = torch.argmax(text_probs)
-print("Output label:", texts[idx])  
-```   
+print("Output label:", texts[idx])
+```