Commit
·
2f91d48
1
Parent(s):
2b4e118
Adding Evaluation Results (#3)
Browse files- Adding Evaluation Results (7423313536fa5afacc12679b6d751a5354e02f89)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -53,4 +53,17 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
| 53 |
|
| 54 |
```
|
| 55 |
|
| 56 |
-
Special thanks to Sushi kek
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
```
|
| 55 |
|
| 56 |
+
Special thanks to Sushi kek
|
| 57 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 58 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__ReMM-L2-13B)
|
| 59 |
+
|
| 60 |
+
| Metric | Value |
|
| 61 |
+
|-----------------------|---------------------------|
|
| 62 |
+
| Avg. | 52.58 |
|
| 63 |
+
| ARC (25-shot) | 59.73 |
|
| 64 |
+
| HellaSwag (10-shot) | 83.1 |
|
| 65 |
+
| MMLU (5-shot) | 54.11 |
|
| 66 |
+
| TruthfulQA (0-shot) | 49.94 |
|
| 67 |
+
| Winogrande (5-shot) | 74.51 |
|
| 68 |
+
| GSM8K (5-shot) | 2.96 |
|
| 69 |
+
| DROP (3-shot) | 43.7 |
|