Commit
•
d36453f
1
Parent(s):
e10c598
remove the leaderboard results from the open-llm-leaderboard pr bot because they dont look good
Browse files
README.md
CHANGED
|
@@ -165,17 +165,3 @@ Commodity cost was ~$240.
|
|
| 165 |
primaryClass={cs.AI}
|
| 166 |
}
|
| 167 |
```
|
| 168 |
-
|
| 169 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 170 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Open-Orca__Mistral-7B-SlimOrca)
|
| 171 |
-
|
| 172 |
-
| Metric | Value |
|
| 173 |
-
|-----------------------|---------------------------|
|
| 174 |
-
| Avg. | 53.34 |
|
| 175 |
-
| ARC (25-shot) | 62.54 |
|
| 176 |
-
| HellaSwag (10-shot) | 83.86 |
|
| 177 |
-
| MMLU (5-shot) | 62.77 |
|
| 178 |
-
| TruthfulQA (0-shot) | 54.23 |
|
| 179 |
-
| Winogrande (5-shot) | 77.43 |
|
| 180 |
-
| GSM8K (5-shot) | 21.38 |
|
| 181 |
-
| DROP (3-shot) | 11.2 |
|
|
|
|
| 165 |
primaryClass={cs.AI}
|
| 166 |
}
|
| 167 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|