EgregiousCube28 minutes ago
Isn't part of the Jev marketing that it has "terra-class intelligence"? I don't know how much it actually achieves that, but unless that's EXTREMELY wrong, it's hard to see how a 0.3B model could claim to be an OS Jev.
putnaop16 minutes ago
agree, maybe os jev is too strong of a wording.
when more people get the idea how to create system one, I am sure Laya will have lots of use cases.
speedping21 minutes ago
So cool. I've fired up pumas (energy monitor) and it seems to run almost fully on the neural engine and not the GPU so it plays really nicely with CoreML
imranq2 hours ago
Based on my admittedly limited research, it seems like you should use Laya for much more deterministic tasks where you have some training data. It won't be as good as Jev for zero shot cases.
jwpapi2 hours ago
I think it can make a lot of sense to make a set with jev and then train laya on that set and do the rest with laya for saving $
putnaop2 hours ago
agree, too good to be true for one shot cases
PaulRobinson5 hours ago
Local LLMs are the future, and one of the reasons I think the data centre furore is just going to end in a market crash.
LLMs that can reliably be used for control problems are the future, and I think classic/deep RL has generally been overlooked for years for a whole host of problems by wider industry because it felt inaccessible. The first thing I thought of when I saw Jev (and then Laya), was "this might move the needle in a really, really interesting way".
Local LLMs that can reliably be used for control problems smash through a lot of barriers I'm interested in, and this intrigues me a lot. Guess I'm about to become a big Laya fan if it can run on this kind of hardware to this performance.
ipsi3 hours ago
The future for whom? The general public? Not a chance, no way, not unless it's able to run on a phone (anywhere from 20-40% of internet users, world-wide, are phone-only).
For companies? I think that's a lot more plausible, as that's mostly just a question of money - is it cheaper to run and administrate our own models, or outsource that?
For technically inclined users? I think that's unlikely unless they're able to operate on relatively cheap hardware while still being just as good as the hosted models. And by that I don't mean "a mac studio," that's far more money than I think is reasonable. A single RTX 5080, maybe, once memory prices start to drop.
Izmaki2 hours ago
Compare the games your average high-end smartphone can run to the AAA titles of the 2010's. It's not a matter of "unless it is able to" but "when it is able to".
frag5 hours ago
that's not a local LLM. If it's local, it doesn't matter in this case. Laya is a System 1 "AI", namely works like a classifier, given a state and questions, it shoots probabilities for each. I publish an episode tomorrow about Laya and Typesafe AI on https://www.youtube.com/@DataScienceatHome
Stay tuned ;)
putnaop2 hours ago
cool, will check it
bigyabai4 hours ago
It won't. Laya is a finetuned version of Google's BeRT model, which is almost 10 years old right now.
If BeRT had any potential to disrupt the datacenter buildout, it already would have.
viraptoran hour ago
Modernbert is from 2024. It's also trained from scratch, not a fine tune.
altano3 hours ago
How much memory does this use of the test machine's (M3 Max) 128 GB unified memory?
WASDx2 hours ago
The model is only 0.3B params so probably not much.
putnaop2 hours ago
Physical footprint: 560.4M Physical footprint (peak): 778.0M
frag5 hours ago
Great job! Did you finetune your own Laya for the snake game or what?
putnaop2 hours ago
its just an example how to run it locally. it takes the laya from official repo with the provided snake example. you can try running it in 2 minutes
tentacleuno5 hours ago
This looks like a local AI model playing Snake -- is that correct? The article offers no explanation.
putnaop2 hours ago
Correct, the cli commands are just copy paste to run on your machine.
ryuuseijin5 hours ago
The linked github project [1] contains more information.
oezi5 hours ago
[dead]
aidiveyt4 hours ago
[dead]