Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -528,3 +528,17 @@ Then you should be ready to generate!
|
|
| 528 |
archivePrefix={arXiv},
|
| 529 |
}
|
| 530 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 528 |
archivePrefix={arXiv},
|
| 529 |
}
|
| 530 |
```
|
| 531 |
+
|
| 532 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 533 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__OpenOrcaxOpenChat-Preview2-13B-GPTQ)
|
| 534 |
+
|
| 535 |
+
| Metric | Value |
|
| 536 |
+
|-----------------------|---------------------------|
|
| 537 |
+
| Avg. | 49.91 |
|
| 538 |
+
| ARC (25-shot) | 61.26 |
|
| 539 |
+
| HellaSwag (10-shot) | 82.14 |
|
| 540 |
+
| MMLU (5-shot) | 57.85 |
|
| 541 |
+
| TruthfulQA (0-shot) | 50.22 |
|
| 542 |
+
| Winogrande (5-shot) | 77.11 |
|
| 543 |
+
| GSM8K (5-shot) | 12.43 |
|
| 544 |
+
| DROP (3-shot) | 8.35 |
|