140
Do you host your own AI? (aussie.zone)
submitted 2 months ago by to c/selfhosted@lemmy.world
200 comments fedilink hide all child comments
 

Do you host your own ML / AI / LLM? What do you use, and what do you use it for?

you are viewing a single comment's thread
view the rest of the comments
[–] 0 points 2 months ago (2 children)

Looping was a problem after reaching a certain context window size. The llama.cpp flags - -flash-attn on and looping penalties helped.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] [S] 2 points 2 months ago* (last edited 2 months ago) (1 child)

    Probably that plus a higher quant solves it. Thing is most of us default to Q4_K_M as "precise enough"... and that seems to be kryptonite for the new Qwen's.

    That's another thing with hosting AI that's not often discussed. Sure, you can maybe run that 27B model...but if it's at Q3_XS it's going to be .... "mentally challenged".

    I've heard the Gemma models with QAT are meant to be near full precision at Q4 size. Haven't tried em yet.

    Actually, on that topic - I've heard there's a different architecture (RWKV), that’s supposed to be much more efficient for long context because it uses an entirely different KV system.

    Sadly, there are few RWKV native models and retraining a standard transformer to RWKV seems like a pain in the ass. I'd need to hire a cloud GPU, distill into a different architecture, mess with datasets .... honestly ICBF.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 2 months ago

    Yeah, a higher quant would be nice, I actually try not to go below Q5, but you can domino’s so much with 16GB of VRAM and the ddr4 system RAM.

    But I must say I‘m pretty impressed by Qwen3.6-35b, not only from its capabilities but also from hardware requirements. MoE for the win I guess.

    RWKV sounds interesting, have to look into it, thanks!

  • permalink
  • fedilink
  • source
  • parent