Qwen2.5 7B Instrauct model fine-tuned on ProverQA [1] rationales created using GPT4o.
[1] Qi, C., Ma, R., Li, B., Du, H., Hui, B., Wu, J., ... & He, C. (2025). Large language models meet symbolic provers for logical reasoning evaluation. arXiv preprint arXiv:2502.06563.