← Search

Liam Fedus

2 accepted papers

2022

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

ICML 2022spotlight

Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However, training these large dense models requires significant amount…

Cited by 765SourcePDFScholar
2021

Do Transformer Modifications Transfer Across Implementations and Applications?

EMNLP 2021main

The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption. In this paper, we comprehensively evaluate many of these modifications in a shared experimental setting that…