Adding Evaluation Results
#25
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 3 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Dolphin2.1-OpenOrca-7B)
|
| 4 |
+
|
| 5 |
+
| Metric | Value |
|
| 6 |
+
|-----------------------|---------------------------|
|
| 7 |
+
| Avg. | 60.47 |
|
| 8 |
+
| ARC (25-shot) | 63.91 |
|
| 9 |
+
| HellaSwag (10-shot) | 84.26 |
|
| 10 |
+
| MMLU (5-shot) | 62.66 |
|
| 11 |
+
| TruthfulQA (0-shot) | 53.84 |
|
| 12 |
+
| Winogrande (5-shot) | 78.22 |
|
| 13 |
+
| GSM8K (5-shot) | 19.94 |
|