We provide a pre-built docker image at ghcr.io/kaist-ina/ns2-flexpass. Use the following command to set-up the docker image. docker pull ghcr.io/kaist-ina/ns2 ...
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.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback