Reading Comprehension on Belebele EL
0.6733AccuracyLayerMoE
Evaluation Results
| Method | Links | |
|---|---|---|
| LayerMoEBackbone=Llama-3.2-3B, Stage=Stage 2, #Experts=842026.03 | 0.6733 | |
| LayerMoE-S1Backbone=Llama-3.2-3B, Stage=Stage 1, #Experts=842026.03 | 0.6633 | |
| Llama-3.2-3B DenseBackbone=Llama-3.2-3B, Stage=Dense, #Experts=-2026.03 | 0.6522 | |
| NeuronMoEBackbone=Llama-3.2-3B, Stage=Stage 2, #Experts=49 (-42%)2026.03 | 0.6456 | |
| NeuronMoE-ENBackbone=Llama-3.2-3B, Stage=Stage 1, #Experts=37 (-56%)2026.03 | 0.6367 | |
| NeuronMoE-S1Backbone=Llama-3.2-3B, Stage=Stage 1, #Experts=49 (-42%)2026.03 | 0.6356 | |
| NeuronMoE-S1Backbone=Qwen-1.5-1.8B, Stage=Stage 1, #Experts=36 (-50%)2026.03 | 0.32 | |
| LayerMoE-S1Backbone=Qwen-1.5-1.8B, Stage=Stage 1, #Experts=722026.03 | 0.3144 |