Update benchmarks in README
Browse files
README.md
CHANGED
|
@@ -67,13 +67,14 @@ In AlpacaEval, Rocket 🦝 achieves a near 80% win rate, coupled with an average
|
|
| 67 |
|
| 68 |
| Metric | Value |
|
| 69 |
|-----------------------|---------------------------|
|
|
|
|
| 70 |
| ARC (25-shot) | 50.51 |
|
| 71 |
-
| HellaSwag (
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
| Winogrande (5-shot) | 67.8 |
|
| 75 |
| GSM8K (5-shot) | 37.91 |
|
| 76 |
-
|
|
| 77 |
|
| 78 |
|
| 79 |
## Intended uses & limitations
|
|
|
|
| 67 |
|
| 68 |
| Metric | Value |
|
| 69 |
|-----------------------|---------------------------|
|
| 70 |
+
| Average | 51.00 |
|
| 71 |
| ARC (25-shot) | 50.51 |
|
| 72 |
+
| HellaSwag (10-shot) | 76.45 |
|
| 73 |
+
| MMLU (5-shot) | 45.51 |
|
| 74 |
+
| TruthfulQA (0-shot) | 54.38 |
|
| 75 |
| Winogrande (5-shot) | 67.8 |
|
| 76 |
| GSM8K (5-shot) | 37.91 |
|
| 77 |
+
| DROP (3-shot) | 24.49 |
|
| 78 |
|
| 79 |
|
| 80 |
## Intended uses & limitations
|