• 24 Posts
  • 556 Comments
Joined 2 years ago
cake
Cake day: June 10th, 2023

help-circle




  • These are the answers they gave the first time.

    Qwencoder is persistent after 6 rerolls.

    Anyways, how do I make these use my gpu? ollama logs say the model will fit into vram / offloaing all layers but gpu usage doesn’t change and cpu gets the load. And regardless of the model size vram usage never changes and ram only goes up by couple hundred megabytes. Any advice? (Linux / Nvidia) Edit: it didn’t have cuda enabled apparently, fixed now



  • Lojcs@lemm.eetoMicroblog Memes@lemmy.worldWhat happened?
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    4
    ·
    edit-2
    25 days ago

    Maybe you don’t understand the point? The post says that internet used to be a force for democracy and is now ‘weaponised’ against it. I’m pointing out that internet itself was never a force and it is silly to try to assign such values to it


  • Lojcs@lemm.eetoMicroblog Memes@lemmy.worldWhat happened?
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    3
    ·
    25 days ago

    I’m not taking about neutral as in in the middle. The medium through which you communicate doesn’t favor any message over any other. So it should only be judged based on how good it is at relaying messages, not who has more access to the medium or what they use it to relay.