Aggregate General Language Modeling on Average 10 Benchmarks
70.04Average ScoreFineRMoE
Evaluation Results
| Method | Links | |
|---|---|---|
| FineRMoEBase Model=Qwen2.5-7B, #P/B=26.65, #AP/B=7.942026.03 | 70.04 | |
| C32A2Base Model=Qwen2.5-7B, #P/B=184.42, #AP/B=13.332026.03 | 69.92 | |
| PTBase Model=Qwen2.5-7B, #P/B=7.62, #AP/B=7.622026.03 | 68.91 | |
| CTBase Model=Qwen2.5-7B, #P/B=7.62, #AP/B=7.622026.03 | 68.62 | |
| NVShardBase Model=Qwen2.5-7B, #P/B=47.55, #AP/B=7.632026.03 | 65.18 | |
| FineRMoEBase Model=Qwen2.5-1.5B, #P/B=5.64, #AP/B=1.852026.03 | 56.62 | |
| C32A2Base Model=Qwen2.5-1.5B, #P/B=37.62, #AP/B=2.942026.03 | 56.5 | |
| PTBase Model=Qwen2.5-1.5B, #P/B=1.54, #AP/B=1.542026.03 | 55.39 | |
| CTBase Model=Qwen2.5-1.5B, #P/B=1.54, #AP/B=1.542026.03 | 55.18 | |
| NVShardBase Model=Qwen2.5-1.5B, #P/B=9.88, #AP/B=1.782026.03 | 52.14 | |
| FineRMoEBase Model=Qwen2.5-0.5B, #P/B=1.68, #AP/B=0.652026.03 | 41.39 | |
| CTBase Model=Qwen2.5-0.5B, #P/B=0.49, #AP/B=0.492026.03 | 41.31 | |
| C32A2Base Model=Qwen2.5-0.5B, #P/B=10.36, #AP/B=0.952026.03 | 41.28 | |
| PTBase Model=Qwen2.5-0.5B, #P/B=0.49, #AP/B=0.492026.03 | 41.19 | |
| NVShardBase Model=Qwen2.5-0.5B, #P/B=2.83, #AP/B=0.632026.03 | 37.14 | |
| S16A4Base Model=Qwen2.5-7B, #P/B=7.62, #AP/B=3.342026.03 | 35.77 | |
| S16A4Base Model=Qwen2.5-1.5B, #P/B=1.78, #AP/B=0.912026.03 | 26.32 | |
| DUBase Model=Qwen2.5-7B, #P/B=47.54, #AP/B=13.322026.03 | 25.85 | |
| S16A4Base Model=Qwen2.5-0.5B, #P/B=0.63, #AP/B=0.402026.03 | 24.18 | |
| DUBase Model=Qwen2.5-1.5B, #P/B=9.87, #AP/B=2.932026.03 | 23.5 | |
| DUBase Model=Qwen2.5-0.5B, #P/B=2.83, #AP/B=0.942026.03 | 22.62 |