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

    • Kichae@lemmy.ca
      0·
      8 måneder siden

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

    • Knusper@feddit.de
      0·
      8 måneder siden

      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…

      • Munkisquisher@lemmy.nz
        0·
        8 måneder siden

        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

      • SpooksMcDoots@mander.xyz
        0·
        8 måneder siden

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

      • 0x4E4F@sh.itjust.worksEnglish
        0·
        8 måneder siden

        I guess… why not… but the db is probably huge, like in the hundreds of GB (maybe even TB… who knows), can’t run that offline.

      • ashe@lemmy.starless.one
        0·
        8 måneder siden

        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.