This paper releases seven open-source MoE language models with full training artifacts and reports up to 3.4 point accuracy gains over dense baselines at equal FLOPs.
On the representation collapse of sparse mixture of experts.Proc
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models
This paper releases seven open-source MoE language models with full training artifacts and reports up to 3.4 point accuracy gains over dense baselines at equal FLOPs.