Like if I type “I have two appl…” for example, often it will suggest “apple” singular instead of plural. Just a small example, but it is really bad at predicting which variant of a word should come after the previous

    • Knusper@feddit.de
      link
      fedilink
      arrow-up
      5
      ·
      10 months ago

      I guess, the real question is: Could we be using (simplistic) LLMs on a phone for predictive text?

      There’s some LLMs that can be run offline and which maybe wouldn’t use enormous amounts of battery. But I don’t know how good the quality of those is…

      • ashe@lemmy.starless.one
        link
        fedilink
        arrow-up
        26
        ·
        edit-2
        10 months ago

        You can run an LLM on a phone (tried it myself once, with llama.cpp), but even on the simplest model I could find it was doing maybe one word every few seconds while using up 100% of the CPU. The quality is terrible, and your battery wouldn’t last an hour.

      • Munkisquisher@lemmy.nz
        link
        fedilink
        arrow-up
        5
        ·
        10 months ago

        A pre trained model isn’t going to learn how you type the more you use it. Though with Microsoft owning SwiftKey, I imagine they will try it soon

        • SidewaysHighways@lemmy.world
          link
          fedilink
          arrow-up
          5
          ·
          10 months ago

          I was so heartbroken when I found out that Microsoft purchased Swiftkey. It was my favorite. Is there any way to still use it without Microsoft involved? Lawdhammercy

        • Square Singer@feddit.de
          link
          fedilink
          arrow-up
          3
          arrow-down
          1
          ·
          10 months ago

          They’ll probably have to offload that to a server farm in real time. That’s not gonna be easy.

      • SpooksMcDoots@mander.xyz
        link
        fedilink
        arrow-up
        1
        ·
        10 months ago

        Openhermes 2.5 Mistral 7b competes with LLMs that require 10x the resources. You could try it out on your phone.

    • Kichae@lemmy.ca
      link
      fedilink
      arrow-up
      4
      arrow-down
      1
      ·
      10 months ago

      The algorithms are the same. The models are different, being trained on a smaller data set.