Upload README.md
Browse files
README.md
CHANGED
|
@@ -372,5 +372,18 @@ print(decoded[0])
|
|
| 372 |
# Why It's benchmark score is lower than preview version?
|
| 373 |
|
| 374 |
**Apparently**, Preview model uses Alpaca Style prompt which has no pre-fix. But ChatML do.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 375 |
|
| 376 |
<!-- original-model-card end -->
|
|
|
|
| 372 |
# Why It's benchmark score is lower than preview version?
|
| 373 |
|
| 374 |
**Apparently**, Preview model uses Alpaca Style prompt which has no pre-fix. But ChatML do.
|
| 375 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 376 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_maywell__Synatra-7B-v0.3-RP)
|
| 377 |
+
|
| 378 |
+
| Metric | Value |
|
| 379 |
+
|-----------------------|---------------------------|
|
| 380 |
+
| Avg. | 57.38 |
|
| 381 |
+
| ARC (25-shot) | 62.2 |
|
| 382 |
+
| HellaSwag (10-shot) | 82.29 |
|
| 383 |
+
| MMLU (5-shot) | 60.8 |
|
| 384 |
+
| TruthfulQA (0-shot) | 52.64 |
|
| 385 |
+
| Winogrande (5-shot) | 76.48 |
|
| 386 |
+
| GSM8K (5-shot) | 21.15 |
|
| 387 |
+
| DROP (3-shot) | 46.06 |
|
| 388 |
|
| 389 |
<!-- original-model-card end -->
|