Jialiang's Blog

Home

❯

Knowledge

❯

learn llm training strategy rlhf

learn llm training strategy -- rlhf

2023年6月13日1分钟阅读

  • llm

大模型RLHF过程

read-list:

  • https://huggingface.co/blog/zh/rlhf
  • https://zhuanlan.zhihu.com/p/624589622
  • https://www.youtube.com/watch?v=2MBJOuVq380&t=4s
  • https://www.youtube.com/watch?v=3ZjXgqVDOzE&list=PLWnsVgP6CzaelCF_jmn5HrpOXzRAPNjWj&index=12

Instruction Tuning

  • https://www.youtube.com/watch?v=zfIGAwD1jOQ

关系图谱

  • 大模型RLHF过程
  • Instruction Tuning

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community