Commit
•
26b30a0
1
Parent(s):
f8988da
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (7f9eda7298f5127fded5a3cc0ec40731beb49acf)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -21,4 +21,17 @@ Samantha-Nebula-7B is a merge of [ehartford/samantha-mistral-7b](https://hugging
|
|
| 21 |
| ARC (25-shot) | |
|
| 22 |
| HellaSwag (10-shot) | |
|
| 23 |
| MMLU (5-shot) | |
|
| 24 |
-
| TruthfulQA (0-shot) | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
| ARC (25-shot) | |
|
| 22 |
| HellaSwag (10-shot) | |
|
| 23 |
| MMLU (5-shot) | |
|
| 24 |
+
| TruthfulQA (0-shot) | |
|
| 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_Weyaxi__Samantha-Nebula-7B)
|
| 27 |
+
|
| 28 |
+
| Metric | Value |
|
| 29 |
+
|-----------------------|---------------------------|
|
| 30 |
+
| Avg. | 52.87 |
|
| 31 |
+
| ARC (25-shot) | 57.0 |
|
| 32 |
+
| HellaSwag (10-shot) | 82.25 |
|
| 33 |
+
| MMLU (5-shot) | 54.21 |
|
| 34 |
+
| TruthfulQA (0-shot) | 49.58 |
|
| 35 |
+
| Winogrande (5-shot) | 73.09 |
|
| 36 |
+
| GSM8K (5-shot) | 11.37 |
|
| 37 |
+
| DROP (3-shot) | 42.57 |
|