Commit
•
86230b3
1
Parent(s):
9bc5b68
Update README.md
Browse files
README.md
CHANGED
|
@@ -397,6 +397,17 @@ You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
|
|
| 397 |
### UGI results inconsistency
|
| 398 |
Please see: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/discussions/56
|
| 399 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 400 |
|
| 401 |
## Other stuff
|
| 402 |
- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
|
|
|
|
| 397 |
### UGI results inconsistency
|
| 398 |
Please see: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/discussions/56
|
| 399 |
|
| 400 |
+
### Benchmarks
|
| 401 |
+
|
| 402 |
+
| Metric |Value|
|
| 403 |
+
|-------------------|----:|
|
| 404 |
+
|Avg. |19.05|
|
| 405 |
+
|IFEval (0-Shot) |37.13|
|
| 406 |
+
|BBH (3-Shot) |25.00|
|
| 407 |
+
|MATH Lvl 5 (4-Shot)| 7.85|
|
| 408 |
+
|GPQA (0-shot) | 7.38|
|
| 409 |
+
|MuSR (0-shot) | 9.56|
|
| 410 |
+
|MMLU-PRO (5-shot) |27.39|
|
| 411 |
|
| 412 |
## Other stuff
|
| 413 |
- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
|