News
verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
[Feature]: Add Support for Google Gemini API as an LLM Option Agent TARS Contribution Welcome Feature New feature or request ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results