Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -161,3 +161,17 @@ response_str = tokenizer.batch_decode(response, skip_special_tokens=False, clean
|
|
| 161 |
print(response_str)
|
| 162 |
```
|
| 163 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
print(response_str)
|
| 162 |
```
|
| 163 |
|
| 164 |
+
|
| 165 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 166 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_wenge-research__yayi-7b-llama2)
|
| 167 |
+
|
| 168 |
+
| Metric | Value |
|
| 169 |
+
|-----------------------|---------------------------|
|
| 170 |
+
| Avg. | 43.62 |
|
| 171 |
+
| ARC (25-shot) | 54.78 |
|
| 172 |
+
| HellaSwag (10-shot) | 77.94 |
|
| 173 |
+
| MMLU (5-shot) | 41.35 |
|
| 174 |
+
| TruthfulQA (0-shot) | 44.02 |
|
| 175 |
+
| Winogrande (5-shot) | 74.51 |
|
| 176 |
+
| GSM8K (5-shot) | 6.67 |
|
| 177 |
+
| DROP (3-shot) | 6.04 |
|