valpy/if_from_base_qwen2.5

This is an IF-RLVR trained model on IFTrain and IFEval constraints, with Qwen/Qwen2.5-7B as the base model.

Citation

If IFBench, IFTrain, or any of the related materials were helpful to your work, please cite:

@article{pyatkin2025generalizing,
  title={Generalizing Verifiable Instruction Following},
  author={Pyatkin, Valentina and Malik, Saumya and Graf, Victoria and Ivison, Hamish and Huang, Shengyi and Dasigi, Pradeep and Lambert, Nathan and Hajishirzi, Hannaneh},
  journal={Advances in Neural Information Processing Systems},
  volume={38},
  year={2025}
}