grpo

Community

Robust RLHF with group-relative policy training.

Authoratrawog
Version1.0.0
Installs0

System Documentation

What problem does it solve?

GRPO enables scalable RLHF refinement by using group-relative rewards to compare multiple completions per prompt and steer policy updates toward higher-reward responses, all while maintaining stability during training.

Core Features & Use Cases

  • RLHF-aligned policy optimization using GRPOConfig and GRPOTrainer
  • Thinking-aware reward signals and token-based evaluation patterns
  • Research-oriented workflow for reward design, alignment, and stable RLHF pipelines

Quick Start

Provide a minimal GRPO training run using your model and a small prompt dataset to begin thinking-aware refinement.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: grpo
Download link: https://github.com/atrawog/overthink-plugins/archive/main.zip#grpo

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.