Need help?
<- Back

Comments (32)

  • woah
    The heavy reliance on eval datasets showcased here and also evidenced by the frontier lab's high payments for such data cast doubt on the claims that AI will become self-improving soon
  • xlayn
    Snap, no gguf to download, will wait for one to appear to test, any improvement over an already good model is good news."18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.
  • pkoiralap
    Sabi-noema also looks like a close competitor in the same space. Built from qwen3.8 and made better.https://huggingface.co/sabicap/sabi-noemaAlso HF model here: https://huggingface.co/RadixArk/DaisyRose-27B
  • jacquesm
    I always wonder what you lose when you start maxing out some specific benchmark. It is really hard to do this in a balanced way and I would love if everybody that did these kind of efforts would take the time to also list the before/afters of a number of other benchmarks that they did not use in their training.
  • mips_avatar
    How did you guys set up the RL topology? Were you guys doing individual RL nodes (4xh200 rollout/4xh200 train) or did you have dedicated trainer and rollout nodes?
  • robertkarl
    I look forward to testing this against my private eval set to determine if it's benchmaxxing or actual improvement based on just 1200 tasks. downloading it now
  • XCSme
    Is it post-training or bench-maxxing?
  • anon
    undefined
  • octoberfranklin
    FWIW that is about $331,000 on low-onboarding-grief clouds (e.g. vast.ai) right now using the SXM variants they used.You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.
  • amarinhodev
    [flagged]