Comment on Llama 3.1 AI Models Have Officially Released

• brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

  At long context, Nemo is way better than llama 8B in my testing.

  Turns out they are both very sensitive to quantization though.

  source

  • ObsidianZed@lemmy.world ⁨2⁩ ⁨months⁩ ago

    My impression is the general consensus is we don’t want huge corporations stealing data to train their AI models only to turn around and cram it down our throats anywhere they can with increasingly negative experiences. That being said, while I would generally agree with that, I still find it interesting and especially if I can host it myself.

    source
  • admin@lemmy.my-box.dev ⁨2⁩ ⁨months⁩ ago

    Yeah, there’s a massive negative circlejerk going on, but mostly with parroted arguments. Being able to locally run a model with this kind of context is huge. Can’t wait for the finetunes that will result from this (*cough* NeverSleep’s *-maid models come to mind).

    source

    • brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

      I am looking into doing it on the 12B for myself TBH, not so much for RP but novel style prose.

      source

      • admin@lemmy.my-box.dev ⁨2⁩ ⁨months⁩ ago

        Ah, that’s a wonderful use case. One of my favourite models has a storytelling lora applied to it, maybe that would be useful to you too?

        At any rate, if you’d end up publishing your model, I’d love to hear about it.

        source

        • -> View More Comments
  • bilb@lem.monster ⁨2⁩ ⁨months⁩ ago

    If forced to characterize the attitude of lemmy towards LLM/“AI,” I’d say people here are broadly interested in the tech but critical of the way it’s often used.

    source

    • General_Effort@lemmy.world ⁨2⁩ ⁨months⁩ ago

      If by interested you mean willing to bullshit… Talking about AI here is like talking about evolution at bible camp in the deep south.

      source
    • brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

      I dunno, with image models specifically it seems like they’re the devil because of the datasets they’re trained on, killing artists, and… that’s that. And LLMs to a lesser extent.

      I think most people don’t realize how much of an inflection point local running vs. corporate hosting could be, which is especially ironic on Lemmy.

      source
  • Halosheep@lemm.ee ⁨2⁩ ⁨months⁩ ago

    The loud minority is really loud.

    source
• admin@lemmy.my-box.dev ⁨2⁩ ⁨months⁩ ago

  I haven’t given it a very thorough testing, and I’m by no means an expert, but from the few prompts I’ve ran so far, I’d have to hand it to Nemo concerning quality.

  Using openrouter.ai, I’ve also given llama3.1 405B a shot, and that seems to be at least on par with (if not better than) Claude 3.5 Sonnet, whilst being a bit cheaper as well.

  source

  • brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

    Llama 70B is probably where its at, if you go the API route. It’s distilled from 405B, and its benchmarks are pretty close.

    source