Commit
•
dbe59a7
1
Parent(s):
8282180
Adding Evaluation Results (#7)
Browse files- Adding Evaluation Results (5423534720f9e62756c3c5c22e837fefbd0f3876)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -100,4 +100,17 @@ To cite this model, please use
|
|
| 100 |
journal={arXiv preprint arXiv:2101.00027},
|
| 101 |
year={2020}
|
| 102 |
}
|
| 103 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
journal={arXiv preprint arXiv:2101.00027},
|
| 101 |
year={2020}
|
| 102 |
}
|
| 103 |
+
```
|
| 104 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 105 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_EleutherAI__gpt-neo-1.3B)
|
| 106 |
+
|
| 107 |
+
| Metric | Value |
|
| 108 |
+
|-----------------------|---------------------------|
|
| 109 |
+
| Avg. | 29.44 |
|
| 110 |
+
| ARC (25-shot) | 31.23 |
|
| 111 |
+
| HellaSwag (10-shot) | 48.47 |
|
| 112 |
+
| MMLU (5-shot) | 24.82 |
|
| 113 |
+
| TruthfulQA (0-shot) | 39.63 |
|
| 114 |
+
| Winogrande (5-shot) | 56.91 |
|
| 115 |
+
| GSM8K (5-shot) | 0.45 |
|
| 116 |
+
| DROP (3-shot) | 4.6 |
|