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.
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?
Can play Doom too - https://x.com/vinnylarouge/status/2100281651930513460
https://xxcancel.com/vinnylarouge/status/2100281651930513460
That was super quick.
Insane
https://x.com/harshagundal/status/2100044305536889015?s=20
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.
I like it! I suspect Jev may have more going on under the hood, but I like the idea of efficient universal transformers
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.
All incorrect answers are marked with low-P.
It (DiffusionGemma with the Jev mode) can also solve an ASCII maze.
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?