斯坦福ChatGPT: Prompting, Instruction Finetuning, and RLHF

斯坦福ChatGPT: Prompting, Instruction Finetuning, and RLHF

目录

  • Prompting, Instruction Finetuning, and RLHF
  • Larger and larger models
  • BabyLM Challenge
  • Language models as world models?
  • Language models as multitask assistants?
  • Lecture Plan: From Language Models to Assistants
  • Emergent abilities of large language models: GPT (2018)

Prompting, Instruction Finetuning, and RLHF

本文链接:https://my.lmcjl.com/post/3443.html

展开阅读全文

4 评论

留下您的评论.