Commit
•
8be3652
1
Parent(s):
e65d34e
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (e80497fd95a7fd60db3412aa93c9bc53d2e0ec6c)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -26,4 +26,17 @@ ASSISTANT:
|
|
| 26 |
>
|
| 27 |
>A common cooking method is stir-frying where ingredients like chicken, beef or vegetables are quickly sautéed in oil at high heat until just cooked through. Stir fried green beans would be an example.
|
| 28 |
>
|
| 29 |
-
>Tea has been consumed for thousands of years as part of daily life in China. It is served before meals to cleanse palates and afterward to aid digestion. Teas range from mildly fragrant white teas to robust oolong varieties.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
>
|
| 27 |
>A common cooking method is stir-frying where ingredients like chicken, beef or vegetables are quickly sautéed in oil at high heat until just cooked through. Stir fried green beans would be an example.
|
| 28 |
>
|
| 29 |
+
>Tea has been consumed for thousands of years as part of daily life in China. It is served before meals to cleanse palates and afterward to aid digestion. Teas range from mildly fragrant white teas to robust oolong varieties.
|
| 30 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 31 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Norquinal__llama-2-7b-claude-chat)
|
| 32 |
+
|
| 33 |
+
| Metric | Value |
|
| 34 |
+
|-----------------------|---------------------------|
|
| 35 |
+
| Avg. | 44.54 |
|
| 36 |
+
| ARC (25-shot) | 54.44 |
|
| 37 |
+
| HellaSwag (10-shot) | 80.66 |
|
| 38 |
+
| MMLU (5-shot) | 46.74 |
|
| 39 |
+
| TruthfulQA (0-shot) | 41.39 |
|
| 40 |
+
| Winogrande (5-shot) | 74.9 |
|
| 41 |
+
| GSM8K (5-shot) | 7.73 |
|
| 42 |
+
| DROP (3-shot) | 5.89 |
|