List your company

Language Modeling on ice (val)

23.819PerplexityOLMoE-7B
23.8162423.8348723.853523.87213May 8, 2026

Evaluation results

MethodLinks
OLMoE-7Btransformer layers=16, hidden size=2048, experts=64, routing=top-k=82026.0523.819—
Hi-MoE-7Btransformer layers=16, hidden size=2048, experts=64, routing=top-k=8, grouping=4 hierarchical groups, experts per group=22026.0523.88830