Adding Evaluation Results
#7
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -154,3 +154,17 @@ If you found OpenLLaMA useful in your research or applications, please cite usin
|
|
| 154 |
|
| 155 |
|
| 156 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 154 |
|
| 155 |
|
| 156 |
|
| 157 |
+
|
| 158 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 159 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openlm-research__open_llama_7b)
|
| 160 |
+
|
| 161 |
+
| Metric | Value |
|
| 162 |
+
|-----------------------|---------------------------|
|
| 163 |
+
| Avg. | 37.05 |
|
| 164 |
+
| ARC (25-shot) | 47.01 |
|
| 165 |
+
| HellaSwag (10-shot) | 71.98 |
|
| 166 |
+
| MMLU (5-shot) | 30.49 |
|
| 167 |
+
| TruthfulQA (0-shot) | 34.85 |
|
| 168 |
+
| Winogrande (5-shot) | 67.96 |
|
| 169 |
+
| GSM8K (5-shot) | 1.59 |
|
| 170 |
+
| DROP (3-shot) | 5.5 |
|