As this technology becomes more accessible you can only imagine the possibilities. I dont have a machine fast enough to make this worth it but i might fuck around with it.

  • webghost0101@lemmy.fmhy.ml
    link
    fedilink
    English
    arrow-up
    9
    ·
    1 year ago

    Seems the model used is gpt4all but i have yet to see a good explanation on what gpt4all does that makes it seem like its a trending for consumers which leads me to believe it really is just people confusing its name as being actually comparable to gpt4.

    If you check the leaderboard on huggingface there are a whopping 37 open source large language models with better quality outputs then gpt4all.

    Any good llm interface that allows you to run them locally should allow you to run any of them and you should play around with multiple cause they might all perform at very different speeds depending on your system. Personally i have have used up to Wizard-Vicuna-13B which is listed more then 10 spots above gpt4all and can provides me a decent but dumb conversation in a reasonably slow speed.

    The biggest (64B) models will probably be too slow to 95% of consumers and will get you good gpt-3 like performance at best.

    Unless someone can tell me otherwise i don’t believe that running these for actual productive goals/more then playing around is something i can advise. And putting the focus on just the interface and not the model that does the work seems a bit salespeech like.

  • Catsrules@lemmy.ml
    link
    fedilink
    English
    arrow-up
    7
    ·
    1 year ago

    Oh this looks really neat. Thanks for posting.

    I don’t see any kind of hardware requirements? Do you happen to know what is recommended? Lots of ram? GPU beefly CPU??

    • nottheengineer@feddit.de
      link
      fedilink
      English
      arrow-up
      6
      ·
      1 year ago

      You’ll want a GPU with a lot of VRAM (16GB or more) and system RAM that’s about twice as big.

      CPU doesn’t matter since everything runs on the GPU.

      It also works without a GPU (by running on the CPU), but that’s very slow. In my opinion you shouldn’t bother if you don’t have a GPU that’s up to the task.