Update README.md
Browse files
README.md
CHANGED
|
@@ -66,6 +66,8 @@ Despite the large volume of German CPT data, the model competes well against the
|
|
| 66 |
**Post-CPT Training**:
|
| 67 |
|
| 68 |
The model underwent 3 epochs of Supervised Fine-Tuning (SFT) with 700K samples.
|
|
|
|
|
|
|
| 69 |
**Further Steps**:
|
| 70 |
|
| 71 |
The model was aligned with Direct Preference Optimization (DPO) using 70K samples.
|
|
|
|
| 66 |
**Post-CPT Training**:
|
| 67 |
|
| 68 |
The model underwent 3 epochs of Supervised Fine-Tuning (SFT) with 700K samples.
|
| 69 |
+
|
| 70 |
+
|
| 71 |
**Further Steps**:
|
| 72 |
|
| 73 |
The model was aligned with Direct Preference Optimization (DPO) using 70K samples.
|