You can deploy this model and start earning money today!

opencsg/
csg-wukong-2b-ultrafeedback-chinese-binarized-lowest

Views

No views yet

We apply DPO to opencsg/csg-wukong-2b-smoltalk-chinese, using ultrafeedback-chinese-binarized-lowest as the DPO dataset.
Train 2 epochs, learning rate=5e-6, batchsize=128
This model's evaluation score is higher than that one trained on ultrafeedback-chinese-binarized

opencsg/csg-wukong-2b-ultrafeedback-chinese-binarized-lowest