• CheeseNoodle@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    7 hours ago

    I’ve been looking into local models lately, mostly out of vague paranoia that I should get one up and running before it becomes defacto illegal for normal people to own due to some kind of regulatory capture. Seems fairly doable at the moment though not particularly user friendly.

    • sobchak@programming.dev
      link
      fedilink
      English
      arrow-up
      2
      ·
      6 hours ago

      They’re OK. It’s kinda amazing how much lossy data can be compressed into a 12GB model. They don’t really start to get comparable to the large frontier models until 70B+ parameters, and you would need serious hardware to run those.

      • CheeseNoodle@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        2 hours ago

        Oh I mean with setup, like I can download ollama and a basic model fine enough and get a generic chat bot. But if I want something that can scan through PDFs with direct citation (like the Nvidia LLM) or play a character then suddenly its all git repositiories and cringey youtube tutorials.

        • sobchak@programming.dev
          link
          fedilink
          English
          arrow-up
          1
          ·
          16 minutes ago

          That would be nice. I don’t know how to do that other than programming it yourself with something like langgraph.