240 发简信
IP属地:香港
  • 180
    fa4af583f2c8
    关注 72粉丝 2文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    9281e206f570
    关注 14粉丝 0文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    lab_5ed4
    关注 58粉丝 0文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    2022学统计
    关注 8粉丝 1文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    cppcoder
    关注 53粉丝 4文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    f96e6ac1e767
    关注 20粉丝 0文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    Melon_99f3
    关注 9粉丝 0文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    ZhiYong_3b99
    关注 3粉丝 0文章 0
    写了 0 字,获得了 0 个喜欢
  • 180
    435789bfdeb6
    关注 86粉丝 4文章 0
    写了 0 字,获得了 0 个喜欢
个人介绍
Base LLM has been trained to predict the next word base on text training data, often trained on a large amount of data from the internet and other sources to figure out what's the next most likely word to follow

Instruction Tuned LLM:
has been trained to follow instructions
You start off with a base LLMs that has been trained on a huge amount of text data and further train it further fine tune it
with input and outputs that are instructions and good attempts to follow those instructions call RLHF reinforcement learning to make the system better able to be helpful and follow instructions because instruction tuned LLMs have been trained





If you can't explain it simply, you don't understand it well enough.

Figure out what you love doing and don’t suck at, then try to figure out how to make a living doing that! Don’t be scared. We’re all going to die, it’s just a question of when and how

All problems in computer science can be solved by another level of indirection