The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning

Open Webpage

Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite

Published: 01 Jan 2024, Last Modified: 12 Mar 2025ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0