Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -1 +1,14 @@
|
|
1 |
-
Experimental merge. Details to come if successful.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Experimental merge. Details to come if successful.
|
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_chargoddard__MelangeA-70b)
|
4 |
+
|
5 |
+
| Metric | Value |
|
6 |
+
|-----------------------|---------------------------|
|
7 |
+
| Avg. | 55.92 |
|
8 |
+
| ARC (25-shot) | 71.25 |
|
9 |
+
| HellaSwag (10-shot) | 87.3 |
|
10 |
+
| MMLU (5-shot) | 70.56 |
|
11 |
+
| TruthfulQA (0-shot) | 60.61 |
|
12 |
+
| Winogrande (5-shot) | 81.53 |
|
13 |
+
| GSM8K (5-shot) | 5.69 |
|
14 |
+
| DROP (3-shot) | 14.53 |
|