Adding Evaluation Results
#5
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -127,4 +127,17 @@ MODEL_CONFIG_MAP = {
|
|
| 127 |
bos_token=None,
|
| 128 |
)
|
| 129 |
}
|
| 130 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
bos_token=None,
|
| 128 |
)
|
| 129 |
}
|
| 130 |
+
```
|
| 131 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 132 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openchat__openchat_8192)
|
| 133 |
+
|
| 134 |
+
| Metric | Value |
|
| 135 |
+
|-----------------------|---------------------------|
|
| 136 |
+
| Avg. | 46.07 |
|
| 137 |
+
| ARC (25-shot) | 59.56 |
|
| 138 |
+
| HellaSwag (10-shot) | 81.44 |
|
| 139 |
+
| MMLU (5-shot) | 46.26 |
|
| 140 |
+
| TruthfulQA (0-shot) | 46.7 |
|
| 141 |
+
| Winogrande (5-shot) | 74.98 |
|
| 142 |
+
| GSM8K (5-shot) | 7.35 |
|
| 143 |
+
| DROP (3-shot) | 6.16 |
|