Skip to content

completion_ids 生成的途径 #17

@lsm2842035890

Description

@lsm2842035890

直接输入input_ids给model得到logits进而得到completion_ids vs 输入input_ids给model.diffusion_generate多步生成completion_ids
这两种方式对grpo训练有什么影响吗,选择后者的原因是什么~

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions