Update README.md
Browse files
README.md
CHANGED
|
@@ -52,3 +52,17 @@ parameters:
|
|
| 52 |
- value: 0.5 # fallback for rest of tensors
|
| 53 |
dtype: bfloat16
|
| 54 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
- value: 0.5 # fallback for rest of tensors
|
| 53 |
dtype: bfloat16
|
| 54 |
```
|
| 55 |
+
|
| 56 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 57 |
+
|
| 58 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PulsarAI__OpenHermes-2.5-neural-chat-v3-3-Slerp)
|
| 59 |
+
|
| 60 |
+
| Metric | Value |
|
| 61 |
+
|-----------------------|---------------------------|
|
| 62 |
+
| Avg. | 71.38 |
|
| 63 |
+
| ARC (25-shot) | 68.09 |
|
| 64 |
+
| HellaSwag (10-shot) | 86.2 |
|
| 65 |
+
| MMLU (5-shot) | 64.26 |
|
| 66 |
+
| TruthfulQA (0-shot) | 62.78 |
|
| 67 |
+
| Winogrande (5-shot) | 79.16 |
|
| 68 |
+
| GSM8K (5-shot) | 67.78 |
|