openpsi-project/ReaLHF

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

⭐ 336 ⑂ 22 Python Apache-2.0 · 2025-04-24推送

distributed-computing distributed-systems large-language-models llm llm-framework llm-training reinforcement-learning transformers deepspeed large-scale-machine-learning reinforcement-learning-from-human-feedback megatron-lm

336

Watchers

0

贡献者

0

Commits

0

Releases

1

Open Issues

2025-04-24

最近推送

原文中文

暂无 README