Adding Evaluation Results
#36
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -214,3 +214,17 @@ You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
|
| 214 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 215 |
}
|
| 216 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 214 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 215 |
}
|
| 216 |
```
|
| 217 |
+
|
| 218 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 219 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_IDEA-CCNL__Ziya-LLaMA-13B-v1)
|
| 220 |
+
|
| 221 |
+
| Metric | Value |
|
| 222 |
+
|-----------------------|---------------------------|
|
| 223 |
+
| Avg. | 25.56 |
|
| 224 |
+
| ARC (25-shot) | 27.73 |
|
| 225 |
+
| HellaSwag (10-shot) | 25.96 |
|
| 226 |
+
| MMLU (5-shot) | 27.04 |
|
| 227 |
+
| TruthfulQA (0-shot) | 48.65 |
|
| 228 |
+
| Winogrande (5-shot) | 49.57 |
|
| 229 |
+
| GSM8K (5-shot) | 0.0 |
|
| 230 |
+
| DROP (3-shot) | 0.0 |
|