Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -68,4 +68,17 @@ Although the aforementioned dataset helps to steer the base language models into
|
|
| 68 |
|
| 69 |
|
| 70 |
|
| 71 |
-
Contact us : [email protected]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
|
| 70 |
|
| 71 |
+
Contact us : [email protected]
|
| 72 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 73 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_quantumaikr__llama-2-70b-fb16-korean)
|
| 74 |
+
|
| 75 |
+
| Metric | Value |
|
| 76 |
+
|-----------------------|---------------------------|
|
| 77 |
+
| Avg. | 56.97 |
|
| 78 |
+
| ARC (25-shot) | 67.15 |
|
| 79 |
+
| HellaSwag (10-shot) | 86.78 |
|
| 80 |
+
| MMLU (5-shot) | 69.29 |
|
| 81 |
+
| TruthfulQA (0-shot) | 56.5 |
|
| 82 |
+
| Winogrande (5-shot) | 82.64 |
|
| 83 |
+
| GSM8K (5-shot) | 29.04 |
|
| 84 |
+
| DROP (3-shot) | 7.42 |
|