Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- opencsg/UltraFeedback-chinese
|
| 5 |
+
language:
|
| 6 |
+
- zh
|
| 7 |
+
base_model:
|
| 8 |
+
- opencsg/csg-wukong-smoltalk-chinese
|
| 9 |
+
---
|
| 10 |
+
* We apply DPO to ``opencsg/csg-wukong-smoltalk-chinese``, using ``ultrafeedback-chinese-binarized`` as the DPO dataset.
|
| 11 |
+
* Train 2 epochs, learning rate=5e-6, batchsize=128
|