Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -31,4 +31,17 @@ OPT-13B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, In
|
|
| 31 |
archivePrefix={arXiv},
|
| 32 |
primaryClass={cs.CL}
|
| 33 |
}
|
| 34 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
archivePrefix={arXiv},
|
| 32 |
primaryClass={cs.CL}
|
| 33 |
}
|
| 34 |
+
```
|
| 35 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 36 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KoboldAI__OPT-13B-Nerybus-Mix)
|
| 37 |
+
|
| 38 |
+
| Metric | Value |
|
| 39 |
+
|-----------------------|---------------------------|
|
| 40 |
+
| Avg. | 34.7 |
|
| 41 |
+
| ARC (25-shot) | 39.85 |
|
| 42 |
+
| HellaSwag (10-shot) | 70.6 |
|
| 43 |
+
| MMLU (5-shot) | 24.9 |
|
| 44 |
+
| TruthfulQA (0-shot) | 34.02 |
|
| 45 |
+
| Winogrande (5-shot) | 67.88 |
|
| 46 |
+
| GSM8K (5-shot) | 0.38 |
|
| 47 |
+
| DROP (3-shot) | 5.26 |
|