• 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
Downloads last month
0
Safetensors
Model size
2.17B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for opencsg/csg-wukong-2b-ultrafeedback-chinese-binarized

Dataset used to train opencsg/csg-wukong-2b-ultrafeedback-chinese-binarized

Collection including opencsg/csg-wukong-2b-ultrafeedback-chinese-binarized