Language Modeling on Wikipedia Yoruba (test)
7.7Perplexity (PPL)Specialist
Evaluation Results
| Method | Links | |
|---|---|---|
| SpecialistBackbone=Pythia-410M, Seeds=137/20262026.03 | 7.7 | |
| KALAVAI (MoE)Backbone=Pythia-410M, Seeds=137/2026, Routing=perfect routing2026.03 | 7.7 | |
| Base modelBackbone=Pythia-410M, Seeds=137/20262026.03 | 41.9 |