I’m curious about what the consensus is here for which models are used for general purpose stuff (coding assist, general experimentation, etc)

What do you consider the “best” model under ~30B parameters?

  • BaroqueInMind@piefed.socialEnglish
    55·
    6 days ago

    Unlike most of you here reading this, I don’t allow a corporate executive/billionaire or a distant nation-state to tell me what I am permitted to say or what my model is allowed to output, so I use an uncensored general model from here (first uncheck “proprietary model” box).

    • Sims@lemmy.mlEnglish
      3·
      4 days ago

      How do you remove all the propaganda they are already trained on ? You reject Deepseek, but you are just allowing yourself to being manipulated by a throng of old propaganda/censorship from the normal internet - garbage manipulative information that is stored in the weights of your ‘uncensored’ model. ‘Freeing’ a model to say “shit”, is not the same as an uncensored model that you can trust. I think we need a dataset cleansed from the current popular ideology and all propaganda against ‘wevil nationstates’ that have just rejected the western/US dominance (giving the middle-finger to western oligarchs)…

      • BaroqueInMind@piefed.socialEnglish
        2·
        6 days ago

        I am running the Irix model.

        You can download and run locally any of the non-proprietary models listed there in that leaderboard, so I don’t understand what you are trying to say by addressing the leaderboard scripts. Since you have no proof of this happening, and I can’t find anything about what you are talking about, you are speaking literal fucking nonsense.

        So please elaborate.

        That paragraph about January 6th and 4chanGPT is making me think you are mentally unstable. Please translate that shit into English for me, because either I’m very dumb or we both are.