Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings: in- and out-of-domain language modeling, zero- and few-shot priming, and full-shot fine-tuning. With the exception of fine-tuning, we find MoEs to be substantially more compute efficient. At more modest training budgets, MoEs can match the performance of dense models using ∼4 times less compute. This gap narrows at scale, but our largest MoE model (1.1T parameters) consistently outperforms a compute-equivalent dense model (6.7B parameters). Overall, this performance gap varies greatly across tasks and domains, suggesting that MoE and dense models generalize differently in ways that are worthy of future study. We make our code and models publicly available for research use.
@article{arxiv.2112.10684,
title = {Efficient Large Scale Language Modeling with Mixtures of Experts},
author = {Mikel Artetxe and Shruti Bhosale and Naman Goyal and Todor Mihaylov and Myle Ott and Sam Shleifer and Xi Victoria Lin and Jingfei Du and Srinivasan Iyer and Ramakanth Pasunuru and Giri Anantharaman and Xian Li and Shuohui Chen and Halil Akin and Mandeep Baines and Louis Martin and Xing Zhou and Punit Singh Koura and Brian O'Horo and Jeff Wang and Luke Zettlemoyer and Mona Diab and Zornitsa Kozareva and Ves Stoyanov},
journal= {arXiv preprint arXiv:2112.10684},
year = {2022}
}