Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
Brand Logo

agnos.is Forums

  1. Home
  2. LocalLLaMA
  3. ELI5 1-bit module.

ELI5 1-bit module.

Scheduled Pinned Locked Moved LocalLLaMA
3 Posts 3 Posters 0 Views
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • W This user is from outside of this forum
    W This user is from outside of this forum
    [email protected]
    wrote on last edited by
    #1

    ELI5 1-bit module. With three attempts, i got nothing out of it, so I assume it's a simpler, more energy efficient model.

    T icecreamtaco@lemmy.worldI 2 Replies Last reply
    1
    0
    • W [email protected]

      ELI5 1-bit module. With three attempts, i got nothing out of it, so I assume it's a simpler, more energy efficient model.

      T This user is from outside of this forum
      T This user is from outside of this forum
      [email protected]
      wrote on last edited by
      #2

      i'm not the smartest out there to explain it but it's like ...instead of floating point numbers as the weights, its just -1,0,1.

      1 Reply Last reply
      1
      0
      • W [email protected]

        ELI5 1-bit module. With three attempts, i got nothing out of it, so I assume it's a simpler, more energy efficient model.

        icecreamtaco@lemmy.worldI This user is from outside of this forum
        icecreamtaco@lemmy.worldI This user is from outside of this forum
        [email protected]
        wrote on last edited by
        #3

        It's a massive performance upgrade, which would make current sized models better and tiny phone-sized models viable. Only problem is that models need to be retrained to use it and afaik, no one significant has done it yet.

        1 Reply Last reply
        1
        0
        • System shared this topic on
        Reply
        • Reply as topic
        Log in to reply
        • Oldest to Newest
        • Newest to Oldest
        • Most Votes


        • Login

        • Login or register to search.
        • First post
          Last post
        0
        • Categories
        • Recent
        • Tags
        • Popular
        • World
        • Users
        • Groups