MiniLLM-gpt2-760M
MiniLLM-gpt2-760M is a gpt2-large (760M) model distilled from gpt2-xlarge (1.5B) on databricks-dolly-15k
Note: MiniLLM requires a SFT model for initilization to perform the PPO optimization.
Evaluation
We ask GPT-4 to give scores for the generated responses of MiniLLM. The prompts are taken from databricks-dolly-15k (test set), self-instruct, and vicuna
Baseline Models
Citation
@inproceedings{minillm,
title={MiniLLM: Knowledge Distillation of Large Language Models},
author={Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
booktitle={Proceedings of ICLR},
year={2024}
}