2
GLM-5.3 Soon (github.com)
submitted 3 months ago by [B] to c/hackernews@lemmy.bestiver.se
comment fedilink hide all child comments
 

Comments

no comments (yet)

sorted by: hot top controversial new old
there doesn't seem to be anything here
11 comments in c/localllama@sh.itjust.works view that post
[–] 5 points 3 months ago (4 children)

glm 5.2 is already pretty good, soo...

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] 2 points 3 months ago (3 children)

    quite large though!

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 3 points 3 months ago (1 child)

    on the extreme opposite side of the spectrum:
    https://huggingface.co/LiquidAI/LFM2.5-2.6B
    or.. really extreme.. https://huggingface.co/AxiomicLabs/GPT-X2.5-135M

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 3 months ago

    Are these any good? I mean, within their size class, obviously - not expecting them to compare to Kimi K3!

    Models the size of that 135M one open up some interesting use cases for edge devices.

  • permalink
  • fedilink
  • source
  • parent
    • [–] [S] 4 points 3 months ago

    Appears they removed the branch and changesets

    Screenshot

  • permalink
  • fedilink
  • source
    •
    [–] 2 points 3 months ago (2 children)

    Very likely the same architecture, just with more post training.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 1 point 3 months ago (1 child)

    What makes you say that? Not arguing, just curious.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 4 points 3 months ago

    Just repeating rumors (sorry, should have been clearer): GLM 5.3 is 5.2 with extra post training, their big upcoming model is 5.5. It kind of makes sense too; pretraining on a new architecture/size is expensive and it's natural for these companies to try to wring an extra minor version or two out of each one.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 2 points 3 months ago

    this has been a crazy few weeks! lol

  • permalink
  • fedilink
  • source
    •
    [–] [S] 1 point 2 months ago

    Update: GLM-5.3 dropped today, open weights release in ~2 weeks!

  • permalink
  • fedilink
  • source
    •