List your company

Language Modeling on Clustered Pre-training Data Cluster 2

18.354Perplexity (PPL)Split MoE
18.3441618.4105818.47718.54342Mar 19, 2026

Evaluation results

MethodLinks
Split MoEModel Variant=Split MoE2026.0318.354
BaseModel Variant=Base2026.0318.6