add eval results
Browse files
README.md
CHANGED
|
@@ -56,4 +56,16 @@ dtype: float16
|
|
| 56 |
|
| 57 |
```
|
| 58 |
|
|
|
|
| 59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
```
|
| 58 |
|
| 59 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 60 |
|
| 61 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PulsarAI__OpenHermes-2.5-neural-chat-v3-2-Slerp)
|
| 62 |
+
|
| 63 |
+
| Metric | Value |
|
| 64 |
+
|-----------------------|---------------------------|
|
| 65 |
+
| Avg. | 70.2 |
|
| 66 |
+
| ARC (25-shot) | 67.49 |
|
| 67 |
+
| HellaSwag (10-shot) | 85.42 |
|
| 68 |
+
| MMLU (5-shot) | 64.13 |
|
| 69 |
+
| TruthfulQA (0-shot) | 61.05 |
|
| 70 |
+
| Winogrande (5-shot) | 80.3 |
|
| 71 |
+
| GSM8K (5-shot) | 63.08 |
|