Scavenging Hyena: Distilling Transformers into Long Convolution Models

Tokiniaina Raharison Ralambomihanta, Shahrad Mohammadzadeh, Sami Nur Islam, Wassim Jabbour, Laurence Liang

Keywords: large language model, hyena, distillation

TL;DR: Evaluating joint knowledge transfer on Hyena-mechanism LLMs.

Abstract: The rapid evolution of Large Language Models (LLMs), epitomized by architectures like GPT-4, has reshaped the landscape of natural language processing. This paper introduces a pioneering approach to address the efficiency concerns associated with LLM pre-training, proposing the use of knowledge distillation for cross-architecture transfer. Leveraging insights from the efficient Hyena mechanism, our method replaces attention heads in transformer models by Hyena, offering a cost-effective alternative to traditional pre-training while confronting the challenge of processing long contextual information, inherent in quadratic attention mechanisms. Unlike conventional compression-focused methods, our technique not only enhances inference speed but also surpasses pre-training in terms of both accuracy and efficiency. In the era of evolving LLMs, our work contributes to the pursuit of sustainable AI solutions, striking a balance between computational power and environmental impact.

Submission Number: 57