Add model card and metadata

README.md

@@ -0,0 +1,30 @@
+---
+license: cc-by-nc-4.0
+library_name: transformers
+pipeline_tag: text-classification
+---
+
+# Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
+
+This model is part of the **MAHALO** (Multi-Action-Head ALignment with PRM-guided DecOding) framework, introduced in the paper [Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards](https://huggingface.co/papers/2510.01167).
+
+MAHALO is a unified framework that standardizes PRM training across verifiable and non-verifiable settings for step-level supervision, performs vectorized multi-objective alignment with Multi-Action-Head DPO, and enables controllable inference through objective-specific weighting and PRM-guided decoding.
+
+This specific checkpoint is a sequence classification model (reward model/PRM) based on the Llama architecture.
+
+## Resources
+
+- **Paper:** [Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards](https://huggingface.co/papers/2510.01167)
+- **Code:** [https://github.com/pearls-lab/multiobj-align](https://github.com/pearls-lab/multiobj-align)
+
+## Citation
+
+```bibtex
+@article{shen2025simultaneous,
+  title={Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards},
+  author={Shen, Yiran and Xia, Yu and Chang, Jonathan and Ammanabrolu, Prithviraj},
+  journal={arXiv preprint arXiv:2510.01167},
+  year={2025},
+  url={https://arxiv.org/abs/2510.01167}
+}
+```