Hi! I'm Niels from the Hugging Face community team. This PR improves the model card for the WG-KV project.
Specifically, it:
- Adds the `text-generation` pipeline tag to the metadata.
- Links the model card to the original research paper: [KV Admission: Learning What to Write for Efficient Long-Context Inference](https://huggingface.co/papers/2512.17452).
- Includes a link to the official GitHub repository for code access.
- Provides a summary and usage instructions for running inference with the provided checkpoints.
Please review and merge if this looks good!
