Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -175,3 +175,17 @@ chinese-alpaca-plus-7b-hf
|
|
175 |
|
176 |
## Reference
|
177 |
- https://github.com/ymcui/Chinese-LLaMA-Alpaca
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
175 |
|
176 |
## Reference
|
177 |
- https://github.com/ymcui/Chinese-LLaMA-Alpaca
|
178 |
+
|
179 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
180 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_shibing624__chinese-alpaca-plus-7b-hf)
|
181 |
+
|
182 |
+
| Metric | Value |
|
183 |
+
|-----------------------|---------------------------|
|
184 |
+
| Avg. | 42.46 |
|
185 |
+
| ARC (25-shot) | 49.23 |
|
186 |
+
| HellaSwag (10-shot) | 70.48 |
|
187 |
+
| MMLU (5-shot) | 38.39 |
|
188 |
+
| TruthfulQA (0-shot) | 39.72 |
|
189 |
+
| Winogrande (5-shot) | 70.09 |
|
190 |
+
| GSM8K (5-shot) | 0.68 |
|
191 |
+
| DROP (3-shot) | 28.61 |
|