Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
3 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_anhnv125__pygmalion-6b-roleplay)
|
4 |
+
|
5 |
+
| Metric | Value |
|
6 |
+
|-----------------------|---------------------------|
|
7 |
+
| Avg. | 33.66 |
|
8 |
+
| ARC (25-shot) | 40.53 |
|
9 |
+
| HellaSwag (10-shot) | 67.47 |
|
10 |
+
| MMLU (5-shot) | 25.73 |
|
11 |
+
| TruthfulQA (0-shot) | 32.53 |
|
12 |
+
| Winogrande (5-shot) | 62.67 |
|
13 |
+
| GSM8K (5-shot) | 1.14 |
|
14 |
+
| DROP (3-shot) | 5.56 |
|