18 citations · 18 across the 1 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 18 cited
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Junyang Lin, An Yang, Jinze Bai +9
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 a…
cs.LG2021
M6-T: Exploring Sparse Expert Models and Beyond
An Yang, Junyang Lin, Rui Men +12
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scal…