← all papers · overview

Distribution-aware Companding Quantization Of Large Language Models

Abstract

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following n tokens using n independent output heads, operating on top of a shared m

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).