Commit
•
0635d60
1
Parent(s):
75741b5
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (6d356b04bb7ab71c7c582498d9e8f0696b062a58)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -76,3 +76,17 @@ This way, the model can better understand the relationship between different par
|
|
| 76 |
## Evaluation
|
| 77 |
|
| 78 |
<B>TODO</B>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
## Evaluation
|
| 77 |
|
| 78 |
<B>TODO</B>
|
| 79 |
+
|
| 80 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 81 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_VMware__open-llama-0.7T-7B-open-instruct-v1.1)
|
| 82 |
+
|
| 83 |
+
| Metric | Value |
|
| 84 |
+
|-----------------------|---------------------------|
|
| 85 |
+
| Avg. | 39.33 |
|
| 86 |
+
| ARC (25-shot) | 46.67 |
|
| 87 |
+
| HellaSwag (10-shot) | 67.67 |
|
| 88 |
+
| MMLU (5-shot) | 28.55 |
|
| 89 |
+
| TruthfulQA (0-shot) | 37.6 |
|
| 90 |
+
| Winogrande (5-shot) | 65.43 |
|
| 91 |
+
| GSM8K (5-shot) | 0.76 |
|
| 92 |
+
| DROP (3-shot) | 28.61 |
|