Commit
•
49d50e4
1
Parent(s):
31ae43d
Update README.md
Browse files
README.md
CHANGED
|
@@ -286,16 +286,3 @@ Then you should be ready to generate!
|
|
| 286 |
archivePrefix={arXiv},
|
| 287 |
}
|
| 288 |
```
|
| 289 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 290 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Open-Orca__OpenOrcaxOpenChat-Preview2-13B)
|
| 291 |
-
|
| 292 |
-
| Metric | Value |
|
| 293 |
-
|-----------------------|---------------------------|
|
| 294 |
-
| Avg. | 50.76 |
|
| 295 |
-
| ARC (25-shot) | 62.37 |
|
| 296 |
-
| HellaSwag (10-shot) | 82.96 |
|
| 297 |
-
| MMLU (5-shot) | 58.68 |
|
| 298 |
-
| TruthfulQA (0-shot) | 51.23 |
|
| 299 |
-
| Winogrande (5-shot) | 77.19 |
|
| 300 |
-
| GSM8K (5-shot) | 14.1 |
|
| 301 |
-
| DROP (3-shot) | 8.75 |
|
|
|
|
| 286 |
archivePrefix={arXiv},
|
| 287 |
}
|
| 288 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|