verl-project/verl

Support Generative Reward Model (GenRM)

Open

#229 建立於 2025年2月9日

在 GitHub 查看
 (17 留言) (0 反應) (1 負責人)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.

貢獻者指南

技術棧
pythonpytorch
領域
machine learningai
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
5
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
needs maintainer response
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
understanding of RLHFfamiliarity with verl architectureknowledge of generative reward modelsPython and PyTorch
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
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.