List your company

Language Modeling on Clustered Pre-training Data Cluster 6

15.097Perplexity (PPL)Split MoE
15.0788415.2014215.32415.44658Mar 19, 2026

Evaluation results

MethodLinks
Split MoEModel Variant=Split MoE2026.0315.097
BaseModel Variant=Base2026.0315.551