Adding Evaluation Results
#18
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -200,3 +200,17 @@ Commodity cost was ~$400.
|
|
| 200 |
primaryClass={cs.AI}
|
| 201 |
}
|
| 202 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
primaryClass={cs.AI}
|
| 201 |
}
|
| 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_Open-Orca__Mistral-7B-OpenOrca)
|
| 206 |
+
|
| 207 |
+
| Metric | Value |
|
| 208 |
+
|-----------------------|---------------------------|
|
| 209 |
+
| Avg. | 54.51 |
|
| 210 |
+
| ARC (25-shot) | 64.08 |
|
| 211 |
+
| HellaSwag (10-shot) | 83.99 |
|
| 212 |
+
| MMLU (5-shot) | 62.24 |
|
| 213 |
+
| TruthfulQA (0-shot) | 53.05 |
|
| 214 |
+
| Winogrande (5-shot) | 77.74 |
|
| 215 |
+
| GSM8K (5-shot) | 19.94 |
|
| 216 |
+
| DROP (3-shot) | 20.53 |
|