Commit
•
c6d4ecf
1
Parent(s):
bc42c77
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (39cf402d8acc70fcdf5c6886ec59bd19233bbe19)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -49,4 +49,17 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
| 49 |
|
| 50 |
```
|
| 51 |
|
| 52 |
-
Special thanks to Sushi kek
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
```
|
| 51 |
|
| 52 |
+
Special thanks to Sushi kek
|
| 53 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 54 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__ReMM-v2-L2-13B)
|
| 55 |
+
|
| 56 |
+
| Metric | Value |
|
| 57 |
+
|-----------------------|---------------------------|
|
| 58 |
+
| Avg. | 50.57 |
|
| 59 |
+
| ARC (25-shot) | 61.95 |
|
| 60 |
+
| HellaSwag (10-shot) | 84.0 |
|
| 61 |
+
| MMLU (5-shot) | 56.14 |
|
| 62 |
+
| TruthfulQA (0-shot) | 50.81 |
|
| 63 |
+
| Winogrande (5-shot) | 75.85 |
|
| 64 |
+
| GSM8K (5-shot) | 13.19 |
|
| 65 |
+
| DROP (3-shot) | 12.08 |
|