Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -25,4 +25,17 @@ assistant role: You are Semica, a helpful AI assistant.
|
|
| 25 |
user: {prompt}
|
| 26 |
assistant:
|
| 27 |
|
| 28 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
user: {prompt}
|
| 26 |
assistant:
|
| 27 |
|
| 28 |
+
```
|
| 29 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 30 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nnpy__Nape-0)
|
| 31 |
+
|
| 32 |
+
| Metric | Value |
|
| 33 |
+
|-----------------------|---------------------------|
|
| 34 |
+
| Avg. | 30.93 |
|
| 35 |
+
| ARC (25-shot) | 32.68 |
|
| 36 |
+
| HellaSwag (10-shot) | 58.68 |
|
| 37 |
+
| MMLU (5-shot) | 24.88 |
|
| 38 |
+
| TruthfulQA (0-shot) | 38.99 |
|
| 39 |
+
| Winogrande (5-shot) | 57.3 |
|
| 40 |
+
| GSM8K (5-shot) | 0.08 |
|
| 41 |
+
| DROP (3-shot) | 3.89 |
|