This is the initial release of LightRFT, a light, efficient, omni-modal & reward-model driven reinforcement fine-tuning framework.

🧠 Rich Algorithm Ecosystem

• Implemented PPO and GRPO algorithms for Large Language Models.
• Added comprehensive interfaces for Reward Model training and inference.

🎯 Innovative Resource Collaboration

• Introduced "Colocate Anything" strategy to maximize GPU memory efficiency by colocating Actor, Critic, and Reward models.

🔧 Flexible Training Strategies

• Integrated DeepSpeed ZeRO and FSDP for scalable distributed training.
• Added PEFT (LoRA) integration for lightweight fine-tuning.

🌐 Environments & Models

• Added support for GSM8K (Math reasoning) and Geo3K (Multimodal) environments and datasets.
• Enabled support for Qwen and DeepSeek model families.

📚 Documentation & Toolkit

• Integrated Weights & Biases (W&B) for training metric logging.
• Released initial Quick Start guide, architecture overview, and reproduction scripts.

Full Changelog: https://github.com/DeepLink-org/LightRFT/commits/v0.1.0

Contributors: Deeplink Team, OpenDILab, System Platform Center and Safe and Trustworthy AI Center at Shanghai AI Laboratory.