Improve model card with metadata and updated links

This PR enhances the model card by:
- Adding the `pipeline_tag: image-feature-extraction` to improve discoverability for models capable of extracting features from images.
- Setting the `license` to `other` in the metadata, as the model uses a custom "OlmoEarth Artifact License". The link to the full license text in `LICENSE.txt` is retained in the content.
- Updating the paper link to point to the official Hugging Face papers page: [OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation](https://huggingface.co/papers/2511.13655).
- Clearly presenting the links to the GitHub repository and the project page for easy access.

README.md

@@ -1,13 +1,14 @@
 ---
-{}
+license: other
+pipeline_tag: image-feature-extraction
 ---
 
 OlmoEarth-v1-Base is a ViT-Base (89M parameters) foundation model for remote sensing tasks over Sentinel-1, Sentinel-2, and Landsat images or image time series.
 
-Please see our GitHub and paper for more information about OlmoEarth.
+This model was presented in the paper [OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation](https://huggingface.co/papers/2511.13655).
 
-- GitHub: https://github.com/allenai/olmoearth_pretrain
-- Paper: https://allenai.org/papers/olmoearth
+*   **GitHub Repository**: https://github.com/allenai/olmoearth_pretrain
+*   **Project Page**: https://olmoearth.allenai.org/
 
 If you are interested in computing embeddings with OlmoEarth, or fine-tuning OlmoEarth for a downstream task, see our tutorials: