metadata
license: apache-2.0
language:
- en
tags:
- mistral
- dpo
- biology
- education
This model is trained on zephyr-7b-beta with FastChat (for SFT) and TRL (for DPO). The purpose is to develop a more capable educational chatbot that helps students learn biology.
If you use this work, please cite: Pedagogical Alignment of Large Language Models https://arxiv.org/abs/2402.05000
@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}
}