Paper ID: 2404.01353

Efficiently Distilling LLMs for Edge Applications

Achintya Kundu, Fabian Lim, Aaron Chew, Laura Wynter, Penny Chong, Rhui Dih Lee

Supernet training of LLMs is of great interest in industrial applications as it confers the ability to produce a palette of smaller models at constant cost, regardless of the number of models (of different size / latency) produced. We propose a new method called Multistage Low-rank Fine-tuning of Super-transformers (MLFS) for parameter-efficient supernet training. We show that it is possible to obtain high-quality encoder models that are suitable for commercial edge applications, and that while decoder-only models are resistant to a comparable degree of compression, decoders can be effectively sliced for a significant reduction in training time.

Submitted: Apr 1, 2024