• ArchRecord@lemm.ee
    link
    fedilink
    English
    arrow-up
    8
    ·
    3 days ago

    I’m running the 1.5b distilled version locally and it seems pretty heavily censored at the weights level to me.

    • Swedneck@discuss.tchncs.de
      link
      fedilink
      arrow-up
      1
      ·
      7 hours ago

      i wouldn’t say it’s heavily censored, if you outright ask it a couple times it will go ahead and talk about things in a mostly objective manner, though with a palpable air of a PR person trying to do damage control.

    • kromem@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      15 hours ago

      There is a reluctance to discuss at a weight level - this graphs out refusals for criticism of different countries for different models:

      https://x.com/xlr8harder/status/1884705342614835573

      But the OP’s refusal is occurring at a provider level and is the kind that would intercept even when the model relaxes in longer contexts (which happens for nearly every model).

      At a weight level, nearly all alignment lasts only a few pages of context.

      But intercepted refusals occur across the context window.