ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

arXiv:2403.03853v1 Announce Type: new
Abstract: As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. However, in this study, we discovered that many layers of LLMs exhibit high similarity, and some layers play a negligible role in network functionality. Based on this observation, we define a metric called Block Influence (BI) to gauge the significance of each layer in LLMs. We then propose a straightforward …

abstract advance arxiv cs.cl current expect however language language models large language large language models llms parameters performance study type