---
license: mit
language:
- en
tags:
- dpo
- biology
- education
- zephyr
---

This model is fine-tuned on zephyr-7b-beta with SFT. The purpose is to develop a more capable educational chatbot that helps students study biology.

If you use this work, please cite:
```
@misc{sonkar2024pedagogical,
      title={Pedagogical Alignment of Large Language Models}, 
      author={Shashank Sonkar and Kangqi Ni and Sapana Chaudhary and Richard G. Baraniuk},
      year={2024},
      eprint={2402.05000},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2402.05000}
}
```