Commit
•
3f98f40
1
Parent(s):
1e74a9c
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (7da1691f333bc7159108c44e1e7aee3679793e9e)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -2,4 +2,17 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
Llama2-7b finetuned on a 10k subset of OpenOrca focusing on multiple choice questions + 6k ShareGPT4 datasets.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
Llama2-7b finetuned on a 10k subset of OpenOrca focusing on multiple choice questions + 6k ShareGPT4 datasets.
|
| 6 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 7 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beaugogh__Llama2-7b-openorca-mc-v2)
|
| 8 |
+
|
| 9 |
+
| Metric | Value |
|
| 10 |
+
|-----------------------|---------------------------|
|
| 11 |
+
| Avg. | 45.88 |
|
| 12 |
+
| ARC (25-shot) | 55.55 |
|
| 13 |
+
| HellaSwag (10-shot) | 81.26 |
|
| 14 |
+
| MMLU (5-shot) | 48.3 |
|
| 15 |
+
| TruthfulQA (0-shot) | 51.49 |
|
| 16 |
+
| Winogrande (5-shot) | 72.85 |
|
| 17 |
+
| GSM8K (5-shot) | 5.38 |
|
| 18 |
+
| DROP (3-shot) | 6.32 |
|