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

Safetensors

Model size

2B 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-lowest

Base model

Finetuned

Finetuned

(2)

this model

opencsg
/

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