Frank Lin comments

Repositories
Issues
Comments

Results 4 comments of


                                            Frank Lin

响应式设计

Great! Thanks.

Reinforcement Learning from Human Feedback (RLHF) examples: Direct Preference Optimization (DPO)

Wait for this, when will the DPO training be supported?

export_model.py 导出ppyoloe_plus model 始终报错(必现)

paddlepaddle降级到2.6.2或者使用 2.6.2的paddlepaddle-gpu可以解决问题

export_model.py 导出ppyoloe_plus model 始终报错(必现)

> > paddlepaddle降级到2.6.2或者使用 2.6.2的paddlepaddle-gpu可以解决问题 > > 怎么安装paddlepaddle-gpu 2.6.2的，安装源是啥也可以在这里找到: ``` https://pypi.org/project/paddlepaddle/#history https://pypi.org/project/paddlepaddle-gpu/#history ```