List your company

Language Modeling on Clustered Pre-training Data Cluster 4

18.414Perplexity (PPL)Split MoE
18.3091219.0170619.72520.43294Mar 19, 2026

Evaluation results

MethodLinks
Split MoEModel Variant=Split MoE2026.0318.414
BaseModel Variant=Base2026.0321.036