• @isolatedscotch@discuss.tchncs.de
      link
      fedilink
      English
      121 year ago

      by run his own models he means locally running a text generation ai on his computer, because sending all that data to openai is a privacy nightmare, especially if you use it for sensitive stuff

      • @XTornado@lemmy.ml
        link
        fedilink
        English
        3
        edit-2
        1 year ago

        But that’s still confusing because we already can. Yeah you might need a little bit more of hardware but… not that crazy. Plus some simpler models can be run with more normal hardware.

        Might not be easy to setup that is true.

        • Communist
          link
          fedilink
          English
          51 year ago

          For large context models the hardware is prohibitively expensive.

          • supert
            link
            fedilink
            English
            11 year ago

            I can run 4bit quantised llama 70B on a pair of 3090s. Or rent gpu server time. It’s expensive but not prohibitive.

            • @anotherandrew@lemmy.mixdown.ca
              link
              fedilink
              English
              11 year ago

              I’m trying to get to the point where I can locally run a (slow) LLM that I’ve fed my huge ebook collection too and can ask where to find info on $subject, getting title/page info back. The pdfs that are searchable aren’t too bad but finding a way to ocr the older TIFF scan pdfs and getting it to “see” graphs/images are areas I’m stuck on.

              • supert
                link
                fedilink
                English
                11 year ago

                3k?Can’t recall exactly, and I’m getting hardwarestability issues.

          • @Grimy@lemmy.world
            link
            fedilink
            English
            11 year ago

            I personally use runpod. It doesn’t cost much even for the high end level stuff. Tbh the openai API is easier though and gives mostly better results.

            • Communist
              link
              fedilink
              English
              11 year ago

              I specifically said “large context” how many tokens can you get through before it goes insanely slow?

              • @Grimy@lemmy.world
                link
                fedilink
                English
                11 year ago

                Max token windows are 4k for llama 2 tho there’s some fine tunes that push the context up further. Speed is limited by your budget mostly, you can stack GPUs and there are most models available (including the really expensive ones)

                I’m just letting you know, If you want something easy, just use ChatGtp. I don’t find them overly expensive for what it is.

            • @isolatedscotch@discuss.tchncs.de
              link
              fedilink
              English
              11 year ago

              nice to see! i’m not following the scene as much anymore (last time i played around with it was with wizard mega 30b). definitely a big improvement, but as much as i hate to do this, i’ll stick to chatgpt for the time being, it’s just better on more niche questions and just does some things plain better (gpt4 can do maths (mostly) without hallucinating)

      • @Agent641@lemmy.world
        link
        fedilink
        English
        -11 year ago

        I use chatgpt as my password manager.

        “Hey robot please record this as the server admin password”

        Then later i dont have to go looking, “hey bruv whats the server admin password?”