> 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.
toasty228 53 minutes ago [-]
In their own demo the left and right panels almost never agree on anything. So it's X times faster but doesn't tell you if it's still right
flockonus 11 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.
toasty228 49 minutes ago [-]
It can be smart and not knowledgeable, as long as all the data is in the question you really don't need much in term of general knowledge, it might be even beneficial to stay on track. It mostly depend son what you do with it. For example in the doom demo I don't think you need astra level knowledge to know "enemy = bad" and "enemy is at my left = turn gun left"
regularfry 1 hours ago [-]
Taking their spiel at face value, it's intended as a mimic of System One in humans. System One is also not smart.
nullbio 8 hours ago [-]
Jev has a 32k context window. I doubt it's a large model.
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 8 hours ago [-]
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.
brainless 7 hours ago [-]
I came across this recently. I was scanning for tiny models from HF using their search API. The script was generated by an agent. When I ran it, Qwen 3.5 did not make it at the top. Turns out, models generally prefer older content (training) but that the scanner also did not give any importance to recency.
FuckButtons 8 hours ago [-]
My guess would be qwen 2.5 predates linear attention which would be more complex to use.
kylehotchkiss 5 hours ago [-]
Anecdotally qwen2.5-14b runs a lot faster on my mini than the small 3 models ¯\_(ツ)_/¯
rollulus 2 hours ago [-]
From the readme
> A Jev-like model takes a piece of text and a list of N text options. It returns one probability for each option. It does this in one pass instead of writing an answer word by word.
I’ve read TypeSafe’s announcement, watched the home assistant demo, and still had no idea what it was. If instead those three sentences were in the announcement…
suresk 5 hours ago [-]
I've seen a lot of LLM uses that are really just zero/few-shot classifiers with a lot of extra steps, so it is interesting to see more models that are taking advantage of all the intelligence encoded in the latent spaces of these models with really efficient output. It feels like this is an under-explored area of LLMs right now and I'm excited to see what comes out of it.
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.
> 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.
Jev is not interesting if it's not "smart", a 1B param model is most definitely not smart.
> A Jev-like model takes a piece of text and a list of N text options. It returns one probability for each option. It does this in one pass instead of writing an answer word by word.
I’ve read TypeSafe’s announcement, watched the home assistant demo, and still had no idea what it was. If instead those three sentences were in the announcement…