BigMaid
Collection
Fun to talk to models.
•
4 items
•
Updated
Warning: This model can produce NSFW content!
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 56.07 |
AI2 Reasoning Challenge (25-Shot) | 61.35 |
HellaSwag (10-Shot) | 85.26 |
MMLU (5-Shot) | 57.15 |
TruthfulQA (0-shot) | 55.29 |
Winogrande (5-shot) | 75.30 |
GSM8k (5-shot) | 2.05 |