jet-rl-enabling-on-policy-fp8-reinforcement-learni

【效率与协作】Implement techniques from Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow. Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs)

独立 GitHub 快照 · 自动分类 · 以原作者文档为准