verl-project/verl

Support Generative Reward Model (GenRM)

Open

#229 创建于 2025年2月9日

在 GitHub 查看
 (17 评论) (0 反应) (1 负责人)Python (21,533 star) (3,940 fork)auto 404
enhancementgood first issue

描述

According to the documentation, veRL only supports AutoModelForSequenceClassification. What would be the best way to implement generative reward model (GenRM) for veRL? I tried looking at FSDP Workers and Megatron-LM Workers but they no longer exist.

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
5
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
needs maintainer response
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
understanding of RLHFfamiliarity with verl architectureknowledge of generative reward modelsPython and PyTorch
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
15
研究方向
Investigate the current reward model implementation in verl, specifically the AutoModelForSequenceClassification support. Review the comments and any linked PRs for proposed designs. Since the referenced workers no longer exist, explore the current actor/critic architecture to identify where GenRM integration would fit. Propose a design that extends the reward model to support generation based scoring.