- We apply DPO to
opencsg/csg-wukong-2b-smoltalk-chinese, usingultrafeedback-chinese-binarizedas the DPO dataset. - Train 2 epochs, learning rate=5e-6, batchsize=128
opencsg/csg-wukong-2b-smoltalk-chinese, using ultrafeedback-chinese-binarized as the DPO dataset.