Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -70,4 +70,17 @@ Example:
|
|
| 70 |
|
| 71 |
|
| 72 |
Official character card: (thanks MortalWombat)
|
| 73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
Official character card: (thanks MortalWombat)
|
| 73 |
+
|
| 74 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 75 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__Samantha-1.1-70b)
|
| 76 |
+
|
| 77 |
+
| Metric | Value |
|
| 78 |
+
|-----------------------|---------------------------|
|
| 79 |
+
| Avg. | 65.74 |
|
| 80 |
+
| ARC (25-shot) | 68.77 |
|
| 81 |
+
| HellaSwag (10-shot) | 87.46 |
|
| 82 |
+
| MMLU (5-shot) | 68.6 |
|
| 83 |
+
| TruthfulQA (0-shot) | 64.85 |
|
| 84 |
+
| Winogrande (5-shot) | 83.27 |
|
| 85 |
+
| GSM8K (5-shot) | 31.61 |
|
| 86 |
+
| DROP (3-shot) | 55.59 |
|