Skip to content

[P1] 正式化 eval 子类型命名和目录结构 #95

@ShadyUnderLight

Description

@ShadyUnderLight

问题

case / rubric / distillation / meta-eval 四种子类型仅靠 evals/README.md 约定区分,未在目录或命名中正式化。

需要做什么

  • 决定是否正式化、采用哪种方案
  • 实施方案并更新相关文档

参考

  • ROADMAP.md P1
  • evals/README.md

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions