YanCotta/post_training_llms

Different post-training techniques for LLMs, including: SFT, DPO and Online RL

⭐ 10 ⑂ 3 Python MIT · 2025-09-05推送

alignment fine-tuning huggingface huggingface-transformers llm pytorch reinforcement-learning sft dpo trl

10

Watchers

0

贡献者

0

Commits

0

Releases

4

Open Issues

2025-09-05

最近推送

原文中文

暂无 README