Adding Evaluation Results
#1
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -66,4 +66,17 @@ Extensive testing is required to characterize Dorflan's capabilities and limitat
|
|
| 66 |
Use this model ethically and do not deploy it for sensitive applications.
|
| 67 |
|
| 68 |
## Contact Information
|
| 69 |
-
Please report issues or concerns with this model to the creator for further investigation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
Use this model ethically and do not deploy it for sensitive applications.
|
| 67 |
|
| 68 |
## Contact Information
|
| 69 |
+
Please report issues or concerns with this model to the creator for further investigation.
|
| 70 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 71 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_formulae__Dorflan)
|
| 72 |
+
|
| 73 |
+
| Metric | Value |
|
| 74 |
+
|-----------------------|---------------------------|
|
| 75 |
+
| Avg. | 47.44 |
|
| 76 |
+
| ARC (25-shot) | 54.44 |
|
| 77 |
+
| HellaSwag (10-shot) | 75.78 |
|
| 78 |
+
| MMLU (5-shot) | 51.36 |
|
| 79 |
+
| TruthfulQA (0-shot) | 51.17 |
|
| 80 |
+
| Winogrande (5-shot) | 72.61 |
|
| 81 |
+
| GSM8K (5-shot) | 0.38 |
|
| 82 |
+
| DROP (3-shot) | 26.37 |
|