Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -33,4 +33,17 @@ ASSISTANT:
|
|
| 33 |
```
|
| 34 |
|
| 35 |
Official character card: (thanks MortalWombat)
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
```
|
| 34 |
|
| 35 |
Official character card: (thanks MortalWombat)
|
| 36 |
+
|
| 37 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 38 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__samantha-1.1-llama-33b)
|
| 39 |
+
|
| 40 |
+
| Metric | Value |
|
| 41 |
+
|-----------------------|---------------------------|
|
| 42 |
+
| Avg. | 54.59 |
|
| 43 |
+
| ARC (25-shot) | 67.83 |
|
| 44 |
+
| HellaSwag (10-shot) | 85.55 |
|
| 45 |
+
| MMLU (5-shot) | 58.79 |
|
| 46 |
+
| TruthfulQA (0-shot) | 61.19 |
|
| 47 |
+
| Winogrande (5-shot) | 76.48 |
|
| 48 |
+
| GSM8K (5-shot) | 4.02 |
|
| 49 |
+
| DROP (3-shot) | 28.29 |
|