We are open-sourcing RISE, our red-teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind, and others.
RISE uses readily available models like Qwen and Gemini Flash under the hood, with no additional training required.
Read more:
Halo is not limited to supervised fine-tuning. It supports async RL and training with external environments.
We are excited to partner with the @sgl_project team to make it the primary engine for rollouts.
Introducing Halo, the best framework for post-training of open-source models.
Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format.
Star us on GitHub: