Adding Evaluation Results (#25)
Browse files- Adding Evaluation Results (06a9a55b604dd7612a24362ce85bc13ee7c1a8b6)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -180,4 +180,17 @@ To cite the GPT-NeoX-20B paper:
|
|
| 180 |
|
| 181 |
copyright = {Creative Commons Attribution 4.0 International}
|
| 182 |
}
|
| 183 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
|
| 181 |
copyright = {Creative Commons Attribution 4.0 International}
|
| 182 |
}
|
| 183 |
+
```
|
| 184 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 185 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_EleutherAI__gpt-neox-20b)
|
| 186 |
+
|
| 187 |
+
| Metric | Value |
|
| 188 |
+
|-----------------------|---------------------------|
|
| 189 |
+
| Avg. | 36.02 |
|
| 190 |
+
| ARC (25-shot) | 45.73 |
|
| 191 |
+
| HellaSwag (10-shot) | 73.45 |
|
| 192 |
+
| MMLU (5-shot) | 25.0 |
|
| 193 |
+
| TruthfulQA (0-shot) | 31.61 |
|
| 194 |
+
| Winogrande (5-shot) | 68.9 |
|
| 195 |
+
| GSM8K (5-shot) | 2.43 |
|
| 196 |
+
| DROP (3-shot) | 5.04 |
|