NOTE: This "diff model" cannot be used directly.
Users have to apply it on top of the original LLaMA weights to get actual Spock weights.
Please find the instructions here: https://github.com/luffycodes/Tutorbot-Spock-Bio.
Spock Model Card
Github details
Please checkout the repo: https://github.com/luffycodes/Tutorbot-Spock-Bio.
Model details
Model type: Spock is an open-source educational tutoring chatbot trained by fine-tuning LLaMA and Vicuna model on synthetic student-tutorbot conversations generated using a specialized prompt.
Model date: Spock was trained between April 2023 and May 2023.
Organizations developing the model: The Spock team with members from Rice University and OpenStax.
Training dataset
700 conversations generated using a specialized prompt from GPT-4. Dataset link: https://huggingface.co/datasets/luffycodes/Tutorbot-Spock-Bio-Dataset
Paper or resources for more information: https://arxiv.org/abs/2305.13272
Code or resources for more information: https://github.com/luffycodes/Tutorbot-Spock-Bio
License: Apache License 2.0
Where to send questions or comments about the model: Shashank Sonkar (ss164@rice.edu)
If you use this work, please cite: CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles https://arxiv.org/abs/2305.13272
@misc{sonkar2023class,
title={CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles},
author={Shashank Sonkar and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk},
year={2023},
eprint={2305.13272},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 17