Adding Evaluation Results
#2
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -12,3 +12,17 @@ Dataset : private dataset.
|
|
| 12 |
Added value : French Language / Writing / Content Creation / Data bias reduction
|
| 13 |
|
| 14 |
Feel free to reach out to us ! contact@faradaylab.fr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
Added value : French Language / Writing / Content Creation / Data bias reduction
|
| 13 |
|
| 14 |
Feel free to reach out to us ! contact@faradaylab.fr
|
| 15 |
+
|
| 16 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 17 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Faradaylab__ARIA-70B-V3)
|
| 18 |
+
|
| 19 |
+
| Metric | Value |
|
| 20 |
+
|-----------------------|---------------------------|
|
| 21 |
+
| Avg. | 60.53 |
|
| 22 |
+
| ARC (25-shot) | 63.91 |
|
| 23 |
+
| HellaSwag (10-shot) | 86.21 |
|
| 24 |
+
| MMLU (5-shot) | 64.75 |
|
| 25 |
+
| TruthfulQA (0-shot) | 51.32 |
|
| 26 |
+
| Winogrande (5-shot) | 82.08 |
|
| 27 |
+
| GSM8K (5-shot) | 28.13 |
|
| 28 |
+
| DROP (3-shot) | 47.29 |
|