slime-rl-training

Community

RL training for LLMs with Megatron-LM.

Authorkwasi-cpu
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill streamlines the complex process of Reinforcement Learning (RL) based post-training for Large Language Models (LLMs), enabling efficient scaling and customization.

Core Features & Use Cases

  • RL Training Framework: Integrates Megatron-LM for efficient distributed training with SGLang for high-throughput inference rollouts.
  • Model Support: Compatible with a wide range of models including GLM, Qwen, DeepSeek, and Llama.
  • Use Case: Fine-tune a Llama 3 model using RLHF to improve its conversational abilities and safety alignment, leveraging custom data generation workflows.

Quick Start

Launch GRPO training for a Qwen3 model using the provided script and data.

Dependency Matrix

Required Modules

sglang-router>=0.2.3raytorch>=2.0.0transformers>=4.40.0

Components

scriptsreferences

💻 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: slime-rl-training
Download link: https://github.com/kwasi-cpu/hermes-agent/archive/main.zip#slime-rl-training

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 471,000+ vetted skills library on demand.