File size: 311 Bytes
aaecefe 67bc6ac aaecefe 67bc6ac aaecefe |
1 2 3 4 5 6 7 8 9 10 11 12 |
---
license: apache-2.0
datasets:
- opencsg/UltraFeedback-chinese
language:
- zh
base_model:
- opencsg/csg-wukong-smoltalk-chinese
---
* We apply DPO to ``opencsg/csg-wukong-2b-smoltalk-chinese``, using ``ultrafeedback-chinese-binarized`` as the DPO dataset.
* Train 2 epochs, learning rate=5e-6, batchsize=128 |