Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -75,3 +75,17 @@ with open(json_filename, "w") as json_file:
|
|
| 75 |
|
| 76 |
print(f"數據已提取並保存為 {json_filename}")
|
| 77 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
|
| 76 |
print(f"數據已提取並保存為 {json_filename}")
|
| 77 |
```
|
| 78 |
+
|
| 79 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 80 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_CHIH-HUNG__llama-2-13b-OpenOrca_20w)
|
| 81 |
+
|
| 82 |
+
| Metric | Value |
|
| 83 |
+
|-----------------------|---------------------------|
|
| 84 |
+
| Avg. | 50.38 |
|
| 85 |
+
| ARC (25-shot) | 59.9 |
|
| 86 |
+
| HellaSwag (10-shot) | 82.51 |
|
| 87 |
+
| MMLU (5-shot) | 56.3 |
|
| 88 |
+
| TruthfulQA (0-shot) | 43.14 |
|
| 89 |
+
| Winogrande (5-shot) | 77.19 |
|
| 90 |
+
| GSM8K (5-shot) | 12.66 |
|
| 91 |
+
| DROP (3-shot) | 20.98 |
|