Reproduce “SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yiping Wang, Hanxian Huang, Yifang Chen, Jishen Zhao, Simon Shaolei Du, Yuandong Tian

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.