List your company

Language Modeling on Clustered Pre-training Data Cluster 1

17.731Perplexity (PPL)Split MoE
17.7172417.8101217.90317.99588Mar 19, 2026

Evaluation results

MethodLinks
Split MoEModel Variant=Split MoE2026.0317.731
BaseModel Variant=Base2026.0318.075