单机多卡进行RLHF在第三步中使用Qwen模型作Actor Model报错

microsoft / DeepSpeedExamples

Example models using DeepSpeed

Apache License 2.0

6.02k stars 1.02k forks source link

Open Dakai798 opened 3 months ago

Dakai798 commented 3 months ago

微信图片_20240625102800

ggbondcxl commented 2 months ago

Hi, I'm also using deepspeedchat for RLHF training qwen, did you solve this problem?