Open Menu
AllLocalCommunitiesAbout
lotide
AllLocalCommunitiesAbout
Login

How Transformers Think: The Information Flow That Makes Language Models Work

⁨7⁩ ⁨likes⁩

Submitted ⁨⁨1⁩ ⁨week⁩ ago⁩ by ⁨cm0002@literature.cafe⁩ to ⁨technology@lemmy.zip⁩

https://www.kdnuggets.com/how-transformers-think-the-information-flow-that-makes-language-models-work

source

Comments

Sort:hotnewtop
  • A_A@lemmy.world ⁨1⁩ ⁨week⁩ ago

    [feed-forward sublayers] … these layers are the mechanism used to gradually learn a general, increasingly abstract understanding of the entire text being processed.

    in my opinion, this is the part that people who hates LLMs (large language models) chooses to ignore.

    source