Adding Evaluation Results
#8
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -84,4 +84,17 @@ The pre-training dataset may contain offensive or inappropriate content even aft
|
|
| 84 |
year = {2021},
|
| 85 |
version = {0.0.1},
|
| 86 |
}
|
| 87 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
year = {2021},
|
| 85 |
version = {0.0.1},
|
| 86 |
}
|
| 87 |
+
```
|
| 88 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 89 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_stabilityai__stablelm-base-alpha-3b)
|
| 90 |
+
|
| 91 |
+
| Metric | Value |
|
| 92 |
+
|-----------------------|---------------------------|
|
| 93 |
+
| Avg. | 27.87 |
|
| 94 |
+
| ARC (25-shot) | 26.45 |
|
| 95 |
+
| HellaSwag (10-shot) | 42.24 |
|
| 96 |
+
| MMLU (5-shot) | 25.43 |
|
| 97 |
+
| TruthfulQA (0-shot) | 40.5 |
|
| 98 |
+
| Winogrande (5-shot) | 53.91 |
|
| 99 |
+
| GSM8K (5-shot) | 0.45 |
|
| 100 |
+
| DROP (3-shot) | 6.14 |
|