Adding Evaluation Results
#5
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -168,3 +168,17 @@ print(output)
|
|
| 168 |
## 开源许可证
|
| 169 |
|
| 170 |
本仓库的代码依照 Apache-2.0 协议开源。模型权重对学术研究完全开放，也可申请免费的商业使用授权（[申请表](https://wj.qq.com/s2/12725412/f7c1/)）。其他问题与合作请联系 <[email protected]>。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
## 开源许可证
|
| 169 |
|
| 170 |
本仓库的代码依照 Apache-2.0 协议开源。模型权重对学术研究完全开放，也可申请免费的商业使用授权（[申请表](https://wj.qq.com/s2/12725412/f7c1/)）。其他问题与合作请联系 <[email protected]>。
|
| 171 |
+
|
| 172 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 173 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_internlm__internlm-20b)
|
| 174 |
+
|
| 175 |
+
| Metric | Value |
|
| 176 |
+
|-----------------------|---------------------------|
|
| 177 |
+
| Avg. | 57.98 |
|
| 178 |
+
| ARC (25-shot) | 60.49 |
|
| 179 |
+
| HellaSwag (10-shot) | 82.13 |
|
| 180 |
+
| MMLU (5-shot) | 61.85 |
|
| 181 |
+
| TruthfulQA (0-shot) | 52.61 |
|
| 182 |
+
| Winogrande (5-shot) | 76.72 |
|
| 183 |
+
| GSM8K (5-shot) | 23.5 |
|
| 184 |
+
| DROP (3-shot) | 48.53 |
|