Commit
•
678bb0b
1
Parent(s):
fd2754e
Adding Evaluation Results (#8)
Browse files- Adding Evaluation Results (cf57d55cb3ca61b38a151634e7457525d6b24a39)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -200,4 +200,17 @@ If you found wizardlm_alpaca_dolly_orca_open_llama_3b useful in your research or
|
|
200 |
journal = {GitHub repository},
|
201 |
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
202 |
}
|
203 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
journal = {GitHub repository},
|
201 |
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
202 |
}
|
203 |
+
```
|
204 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
205 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_3b)
|
206 |
+
|
207 |
+
| Metric | Value |
|
208 |
+
|-----------------------|---------------------------|
|
209 |
+
| Avg. | 35.5 |
|
210 |
+
| ARC (25-shot) | 41.55 |
|
211 |
+
| HellaSwag (10-shot) | 61.52 |
|
212 |
+
| MMLU (5-shot) | 26.79 |
|
213 |
+
| TruthfulQA (0-shot) | 42.42 |
|
214 |
+
| Winogrande (5-shot) | 61.8 |
|
215 |
+
| GSM8K (5-shot) | 0.08 |
|
216 |
+
| DROP (3-shot) | 14.33 |
|