File size: 577 Bytes
c576075 6fb8a9f c576075 cf6f801 712ee75 cf6f801 f3f9d89 |
1 2 3 4 5 6 7 8 9 10 11 |
# palmer
palmer-003 focuses on reaching sota performance by MErging of Experts + fine-tuning, where each expert is consolidated into one model and finally is fine-tuned on useful textual data.
```
### Evaluation
ARC-C OBQA HellaSwag PIQA Winogrande Average
tinyllama | 0.3029 | 0.3600 | 0.5935 | 0.7329 | 0.5959 | 0.5170 |
palmer-002-2401 | 0.3311 | 0.3600 | 0.5981 | 0.7416 | 0.6006 | 0.5266 |
babbage-002 | 0.3285 | 0.3620 | 0.6380 | 0.7606 | 0.6085 | 0.5395 |
palmer-003 | 0.3370 | 0.3740 | 0.6128 | 0.7486 | 0.6535 | 0.5451 |
``` |