Machine Translation on WMT23 En-De (test)
40.9BLEUX-ALMA-13B (Only SFT, MoE)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| X-ALMA-13B (Only SFT, MoE)Parameters=13B, Training Strategy=Only SFT, Architecture=MoE2025.02 | 40.9 | 84.1 | |
| X-ALMA-13B-DAT (MoE)Parameters=13B, Training Strategy=DAT, Architecture=MoE2025.02 | 35.3 | 83.3 | |
| X-ALMA-13B-DATM (MoE)Parameters=13B, Training Strategy=DATM, Architecture=MoE2025.02 | 35.3 | 83.3 | |
| NLLB-3.3BParameters=3.3B2025.02 | 33.5 | 79.7 | |
| Aya-23-35BParameters=35B2025.02 | 30.7 | 80.7 | |
| Aya-23-8BParameters=8B2025.02 | 29.3 | 80.4 | |
| Aya-1012025.02 | 25.1 | 75.1 | |
| LLaMAX3-Alpaca-8BParameters=8B2025.02 | 20.9 | 73.3 |