Adding Evaluation Results
#4
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -44,4 +44,17 @@ OPT-30B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, In
|
|
| 44 |
archivePrefix={arXiv},
|
| 45 |
primaryClass={cs.CL}
|
| 46 |
}
|
| 47 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
archivePrefix={arXiv},
|
| 45 |
primaryClass={cs.CL}
|
| 46 |
}
|
| 47 |
+
```
|
| 48 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 49 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__OPT-30B-Erebus)
|
| 50 |
+
|
| 51 |
+
| Metric | Value |
|
| 52 |
+
|-----------------------|---------------------------|
|
| 53 |
+
| Avg. | 33.67 |
|
| 54 |
+
| ARC (25-shot) | 36.69 |
|
| 55 |
+
| HellaSwag (10-shot) | 65.6 |
|
| 56 |
+
| MMLU (5-shot) | 24.8 |
|
| 57 |
+
| TruthfulQA (0-shot) | 38.76 |
|
| 58 |
+
| Winogrande (5-shot) | 65.11 |
|
| 59 |
+
| GSM8K (5-shot) | 0.23 |
|
| 60 |
+
| DROP (3-shot) | 4.49 |
|