[–] 4 points 3 weeks ago (1 child)

"flash" -> looks inside -> over 200B parameters

i mean i'm sure it's much smaller than the non flash version, but my hope dies pretty quick when i realize i need a datacenter to run a model

  • source
  • [–] 5 points 1 month ago

    that's nice, but at today's pace 3.5 seems a bit dated (3.8 available at time of comment, qwen4 supposedly "soon")

    heretic is a good abliteration method from my experience

    glad it's a 9b model

  • source
  • [–] 7 points 1 month ago

    this, but "2030"

    i quite like blizzard's other shooter, overwatch so i have hope that it could be good

    i like the starcraft universe more than i do any specific RTS mechanic

  • source
  • view more: next ›