Commit
·
51eaa12
1
Parent(s):
31d9ea8
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,3 +17,4 @@ dataset: argilla/distilabel-math-preference-dpo
|
|
| 17 |
---
|
| 18 |
|
| 19 |
This model was finetuned with DPO technique.
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
This model was finetuned with DPO technique.
|
| 20 |
+
The goal was to experiment if the base models capabilities in mathematics can be increased.
|