← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范,页面不展示任何联系方式。 需要更正或删除?通过收录与更正通道提交,24 小时内处理。
代表作品 / 项目
- verl⭐ 23747verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
- OpenRLHF⭐ 10067An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
- secretflow⭐ 2715A unified framework for privacy-preserving data analysis and machine learning
- VeOmni⭐ 2232VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
- verl-omni⭐ 1168Multimodal RL training framework for diffusion & omni models