Improve model card: add paper link, repository link, and model description
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the community science team at Hugging Face.
I noticed this model is part of the Agent-STAR project but the model card is currently empty. This PR improves the documentation by:
- Linking the model to the associated paper: "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe".
- Adding a link to the official GitHub repository.
- Providing a description of the STAR pipeline and specifying that this is the SFT-tuned variant.
- Adding a sample inference snippet based on the repository's instructions.
- Adding the
text-generationpipeline tag for better discoverability.
These changes make the model much more useful for the research community!