• brucethemoose@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    6 days ago

    What model size/family? What GPU? What context length? There are many different backends with different strengths, but I can tell you the optimal way to run it and the quantization you should run with a bit more specificity, heh.

    • hendrik@palaver.p3x.de
      link
      fedilink
      English
      arrow-up
      2
      ·
      edit-2
      6 days ago

      CPU-only. It’s an old Xeon workstation without any GPU, since I mostly do one-off AI tasks at home and I never felt any urge to buy one (yet). Model size woul be something between 7B and 32B with that. Context length is something like 8128 tokens. I have a bit less than 30GB of RAM to waste since I’m doing other stuff on that machine as well.

      And I’m picky with the models. I dislike the condescending tone of ChatGPT and newer open-weight models. I don’t want it to blabber or praise me for my “genious” ideas. It should be creative, have some storywriting abilities, be uncensored and not overly agreeable. Best model I found for that is Mistral-Nemo-Instruct. And I currently run a Q4_K_M quant of it. That does about 2.5 t/s on my computer (which isn’t a lot, but somewhat acceptable for what I do). Mistral-Nemo isn’t the latest and greatest any more. But I really prefer it’s tone of speaking and it performs well on a wide variety of tasks. And I mostly do weird things with it. Let it give me creative advice, be a dungeon master or an late 80s text adventure. Or mimick a radio moderator and feed it into TTS for a radio show. Or write a book chapter or a bad rap song. I’m less concerned with the popular AI use-cases like answer factual questions or write computer code. So I’d like to switch to a newer, more “intelligent” model. But that proves harder than I imagined.

      (Occasionally I do other stuff as well, but that’s a far and in-between. So I’ll rent a datacenter GPU on runpod.io for a few bucks an hour. That’s the main reason why I didn’t buy an own GPU yet.)

      • brucethemoose@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        5 days ago

        One more thing, you don’t have to get something shiny and new to speed LLMs up. Even if you have like a 4-6GB GPU collecting dust somehwere, you can still use it to partially offload MoE models to great effect.

      • brucethemoose@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        5 days ago

        Try any of Latitude’s series. They’re ‘uninhibited’ dungeonmaster models, but they should be smart enough (and retain enough of that personality) for some flexibility:

        https://huggingface.co/LatitudeGames


        Perhaps more optimally for your hardware, try this:

        https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B

        It’s trained from Qwen A3B base, not instruct. Base models usually don’t have the severe ChatGPT-isms you describe, hence while I haven’t personally tried this model, it seems promising. And it should be fast on your Xeon.

        • swelter_spark@reddthat.com
          link
          fedilink
          English
          arrow-up
          3
          ·
          5 days ago

          The 30B-A3Bs I’ve tried have been suuuuuuuper repetitive. Do you have any specific settings to recommend to get them to work well?

          • brucethemoose@lemmy.world
            link
            fedilink
            English
            arrow-up
            3
            ·
            edit-2
            5 days ago

            Random thing, I did not get a notification for this comment, I stumbled upon it. This happens all the time, and it makes me wonder how many replies I miss…

            I don’t run A3B specifically, but for Qwen3 32B Instruct I put something like “vary your prose; avoid repetitive vocabulary and sentence structure” in the system prompt, run at least 0.5 DRY, and maybe some dynamic sampler like mirostat if supported. Too much regular rep penalty makes it dumb, unfortunately.

            But I have much better luck with base model derived models. Look up the finetunes you tried, and see if they were trained from A3B instruct or base. Qwen3 Instruct is pretty overtuned.

            • swelter_spark@reddthat.com
              link
              fedilink
              English
              arrow-up
              1
              ·
              6 hours ago

              They may have been based on Instruct. It left such a bad impression, I didn’t play around with them much. Good to know for the future, though. I haven’t used DRY or mirostat really in the past, but I’ll try them next time I look at the Qwen3s.

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

                Honestly I don’t use Qwen3 instruct unless it’s for code or “logic.” Even the 32B is soo dry and focused on that, and countering it with sampling dumbs it down.

                Not sure if it’s too big, but I have been super impressed with Jamba 52B. It knows tons of fiction trivia and writing styles for such a “small” model, though I haven’t tried to manipulate its prompt for writing yet. And it’s an MoE model like A3B.

        • hendrik@palaver.p3x.de
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          5 days ago

          Big thanks! I’m always looking for recommendations. I’ll check them out. It’s going to take me some time, since it’s very subjective. I used to look at numbers and scores, but they just don’t mean a lot. So I need to use every one for a while and see whether I like what they write. The MoE model is quite an improvement in speed already. It’s 3 times faster…