Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -34,4 +34,17 @@ OPT-6B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, Inc
|
|
| 34 |
archivePrefix={arXiv},
|
| 35 |
primaryClass={cs.CL}
|
| 36 |
}
|
| 37 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
archivePrefix={arXiv},
|
| 35 |
primaryClass={cs.CL}
|
| 36 |
}
|
| 37 |
+
```
|
| 38 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 39 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__OPT-6B-nerys-v2)
|
| 40 |
+
|
| 41 |
+
| Metric | Value |
|
| 42 |
+
|-----------------------|---------------------------|
|
| 43 |
+
| Avg. | 33.87 |
|
| 44 |
+
| ARC (25-shot) | 38.4 |
|
| 45 |
+
| HellaSwag (10-shot) | 68.57 |
|
| 46 |
+
| MMLU (5-shot) | 24.34 |
|
| 47 |
+
| TruthfulQA (0-shot) | 34.73 |
|
| 48 |
+
| Winogrande (5-shot) | 65.59 |
|
| 49 |
+
| GSM8K (5-shot) | 0.68 |
|
| 50 |
+
| DROP (3-shot) | 4.78 |
|