Pedagogical Alignment of Large Language Models
Paper • 2402.05000 • Published
How to use kangqi-ni/Mistral-7B-Instruct-v0.1_bio-tutor_dpo with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="kangqi-ni/Mistral-7B-Instruct-v0.1_bio-tutor_dpo") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("kangqi-ni/Mistral-7B-Instruct-v0.1_bio-tutor_dpo")
model = AutoModel.from_pretrained("kangqi-ni/Mistral-7B-Instruct-v0.1_bio-tutor_dpo", device_map="auto")This model is a fschat fine-tuned version of mistral-7b. The goal is to create a tutorbot 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}
}