Language Understanding on MMLU (Accuracy and Acc Norm)
24.31AccuracyDense 1.3B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Dense 1.3BArchitecture=Dense, Total Parameters=1.3B, Precision=bf16, Shot count=5-shot, Evaluation Framework=lm-eval-harness 0.4.72026.05 | 24.31 | — | |
| Dense 0.7BArchitecture=Dense, Total Parameters=0.7B, Precision=bf16, Shot count=5-shot, Evaluation Framework=lm-eval-harness 0.4.72026.05 | 23.98 | — | |
| MoL 0.61B/2.08BArchitecture=MoL, Total Parameters=2.08B, Active Parameters=0.61B, Precision=bf16, Shot count=5-shot, Evaluation Framework=lm-eval-harness 0.4.72026.05 | 23.07 | — |