Commit
•
a994747
1
Parent(s):
372f6e0
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (72f966a0c7bd05d0e3193c1f6ec9d16b81ffe549)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -77,4 +77,17 @@ print(decoded[0])
|
|
| 77 |
|
| 78 |
# Why It's benchmark score is lower than preview version?
|
| 79 |
|
| 80 |
-
**Apparently**, Preview model uses Alpaca Style prompt which has no pre-fix. But ChatML do.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
# Why It's benchmark score is lower than preview version?
|
| 79 |
|
| 80 |
+
**Apparently**, Preview model uses Alpaca Style prompt which has no pre-fix. But ChatML do.
|
| 81 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 82 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_maywell__Synatra-7B-v0.3-RP)
|
| 83 |
+
|
| 84 |
+
| Metric | Value |
|
| 85 |
+
|-----------------------|---------------------------|
|
| 86 |
+
| Avg. | 57.38 |
|
| 87 |
+
| ARC (25-shot) | 62.2 |
|
| 88 |
+
| HellaSwag (10-shot) | 82.29 |
|
| 89 |
+
| MMLU (5-shot) | 60.8 |
|
| 90 |
+
| TruthfulQA (0-shot) | 52.64 |
|
| 91 |
+
| Winogrande (5-shot) | 76.48 |
|
| 92 |
+
| GSM8K (5-shot) | 21.15 |
|
| 93 |
+
| DROP (3-shot) | 46.06 |
|