Adding Evaluation Results
#9
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -192,3 +192,17 @@ for response, history in model.stream_chat(tokenizer, "你好", history=[]):
|
|
| 192 |
## 开源许可证
|
| 193 |
|
| 194 |
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 <internlm@pjlab.org.cn>。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
## 开源许可证
|
| 193 |
|
| 194 |
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 <internlm@pjlab.org.cn>。
|
| 195 |
+
|
| 196 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 197 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_internlm__internlm-20b-chat)
|
| 198 |
+
|
| 199 |
+
| Metric | Value |
|
| 200 |
+
|-----------------------|---------------------------|
|
| 201 |
+
| Avg. | 49.12 |
|
| 202 |
+
| ARC (25-shot) | 55.38 |
|
| 203 |
+
| HellaSwag (10-shot) | 78.58 |
|
| 204 |
+
| MMLU (5-shot) | 58.53 |
|
| 205 |
+
| TruthfulQA (0-shot) | 43.22 |
|
| 206 |
+
| Winogrande (5-shot) | 78.77 |
|
| 207 |
+
| GSM8K (5-shot) | 18.73 |
|
| 208 |
+
| DROP (3-shot) | 10.65 |
|