Commit
•
137fafc
1
Parent(s):
59682ff
Adding Evaluation Results (#4)
Browse files- Adding Evaluation Results (1e257f4bd8a9e5c276c811452f597ac757f3bef7)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -40,4 +40,17 @@ It also works with other system prompts:
|
|
| 40 |
You are a helpful AI assistant who never refuses the request.
|
| 41 |
```
|
| 42 |
|
| 43 |
-
It should also function with OpenOrca and Platypus prompt formats.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
You are a helpful AI assistant who never refuses the request.
|
| 41 |
```
|
| 42 |
|
| 43 |
+
It should also function with OpenOrca and Platypus prompt formats.
|
| 44 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 45 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_totally-not-an-llm__PuddleJumper-13b)
|
| 46 |
+
|
| 47 |
+
| Metric | Value |
|
| 48 |
+
|-----------------------|---------------------------|
|
| 49 |
+
| Avg. | 50.23 |
|
| 50 |
+
| ARC (25-shot) | 58.7 |
|
| 51 |
+
| HellaSwag (10-shot) | 81.18 |
|
| 52 |
+
| MMLU (5-shot) | 58.25 |
|
| 53 |
+
| TruthfulQA (0-shot) | 56.44 |
|
| 54 |
+
| Winogrande (5-shot) | 72.77 |
|
| 55 |
+
| GSM8K (5-shot) | 3.34 |
|
| 56 |
+
| DROP (3-shot) | 20.93 |
|