Hacker News

Reverse-engineered Jev-like model

• 9 Comments
• Out of curiosity and semi unrelated — why do so many of these projects with customized encoder-decoder setups use earlier Qwen versions like 2.5 and 3 and not the smallest 3.5? Purely the few 100m params, or something else in the latter’s arch or pretraining?

  By vrc a minute ago

• https://x.com/harshagundal/status/2100044305536889015?s=20
  > They were building in stealth for 2 years, I was building in stealth for 2 hours…
  > Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe.

  By steeve 3 hours ago

• No question OSS is amazing, but this video is a satire at best. It doesn't take much attention to see the results on right vs. left side are significantly different.
  Jev is not interesting if it's not "smart", a 1B param model is most definitely not smart.

  By flockonus 3 hours ago

• Any diffusion model is potentially a Jev in disguise: https://github.com/vllm-project/vllm/pull/57250
  Runs ~0.2s per decision on my DGX Spark.

    10/10 programming language detection
    9/10 human language detection
    10/12 unit magnitude comparison
  

  All incorrect answers are marked with low-P.
  It (DiffusionGemma with the Jev mode) can also solve an ASCII maze.

  By mmastrac an hour ago

• I like it! I suspect Jev may have more going on under the hood, but I like the idea of efficient universal transformers

  By tomrod 2 hours ago

• Can play Doom too - https://x.com/vinnylarouge/status/2100281651930513460

  By rochansinha 6 hours ago

• https://xxcancel.com/vinnylarouge/status/2100281651930513460

  By DavCreator 5 hours ago

• That was super quick.

  By _superposition_ 4 hours ago

• Insane

  By looksjjhg 2 hours ago