Remix.run Logo
Reverse-engineered Jev-like model(github.com)
81 points by rochansinha 7 hours ago | 12 comments
steeve 5 hours ago | parent | next [-]

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.

flockonus 4 hours ago | parent [-]

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.

nullbio 16 minutes ago | parent [-]

Jev has a 32k context window. I doubt it's a large model.

mmastrac 2 hours ago | parent | prev | next [-]

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.

vrc an hour ago | parent | prev | next [-]

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?

augment_me 41 minutes ago | parent | next [-]

In my experience if you tell Claude to port LLM-like stuff without explicit steering for versioning, it will default to the most popular thing for this in its training window to reduce errors. 3.5 is outside its training data.

FuckButtons 32 minutes ago | parent | prev [-]

My guess would be qwen 2.5 predates linear attention which would be more complex to use.

rochansinha 7 hours ago | parent | prev | next [-]

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

DavCreator 6 hours ago | parent [-]

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

tomrod 3 hours ago | parent | prev | next [-]

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

_superposition_ 5 hours ago | parent | prev [-]

That was super quick.

looksjjhg 3 hours ago | parent [-]

Insane