Adding Evaluation Results
#6
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -21,4 +21,17 @@ You are a helpful AI assistant.
|
|
| 21 |
|
| 22 |
USER: <prompt>
|
| 23 |
ASSISTANT:
|
| 24 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
USER: <prompt>
|
| 23 |
ASSISTANT:
|
| 24 |
+
```
|
| 25 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 26 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__WizardLM-1.0-Uncensored-Llama2-13b)
|
| 27 |
+
|
| 28 |
+
| Metric | Value |
|
| 29 |
+
|-----------------------|---------------------------|
|
| 30 |
+
| Avg. | 49.31 |
|
| 31 |
+
| ARC (25-shot) | 55.72 |
|
| 32 |
+
| HellaSwag (10-shot) | 80.34 |
|
| 33 |
+
| MMLU (5-shot) | 55.4 |
|
| 34 |
+
| TruthfulQA (0-shot) | 51.44 |
|
| 35 |
+
| Winogrande (5-shot) | 74.66 |
|
| 36 |
+
| GSM8K (5-shot) | 13.27 |
|
| 37 |
+
| DROP (3-shot) | 14.35 |
|