catty

joined 3 days ago
 

I've tried coding and every one I've tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I've tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can't really handle anything above 4B in a timely manner. 8B is about 1 t/s!

[–] catty@lemmy.world 0 points 23 hours ago

I like how all the big media just happened to publish articles about "peaceful protests" to pacify the protestors, "please don't be violent everyone, the police can't shoot you all in the leg with rubber bullets".

The violent protests are the successful ones. Just ask every country, ever.

[–] catty@lemmy.world 1 points 2 days ago* (last edited 2 days ago) (1 children)

But won't this be a mish-mash of different docker containers and projects creating an installation, dependency, upgrade nightmare?

[–] catty@lemmy.world 3 points 2 days ago (1 children)

But its website is Chinese. Also what's the github?

[–] catty@lemmy.world 11 points 2 days ago

It's noise, junk to get attention away from other things.

[–] catty@lemmy.world 3 points 2 days ago (2 children)

This looks interesting - do you have experience of it? How reliable / efficient is it?

[–] catty@lemmy.world 1 points 2 days ago* (last edited 2 days ago)

Try the beta on the github repo, and use a smaller model!

[–] catty@lemmy.world 4 points 3 days ago

I'm getting very-near real-time on my old laptop. Maybe a delay of 1-2s whilst it creates the response

[–] catty@lemmy.world 1 points 3 days ago* (last edited 3 days ago)

I agree. it looks nice, explains the models fairly well, hides away the model settings nicely, and even recommends some initial models to get started that have low requirements. I like the concept of plugins but haven't found a way to e.g. run python code it creates yet and display the output in the window

[–] catty@lemmy.world 9 points 3 days ago* (last edited 3 days ago) (4 children)

I've discovered jan.ai which is far faster than GPT4All, and visually a little nicer.

EDIT: After using it for an hour or so, it seems to crash all the time, I keep on having to reset it, and currently am facing it freezing for no reason.

[–] catty@lemmy.world 1 points 3 days ago
 

I was looking back at some old lemmee posts and came across GPT4All. Didn't get much sleep last night as it's awesome, even on my old (10yo) laptop with a Compute 5.0 NVidia card.

Still, I'm after more, I'd like to be able to get image creation and view it in the conversation, if it generates python code, to be able to run it (I'm using Debian, and have a default python env set up). Local file analysis also useful. CUDA Compute 5.0 / vulkan compatibility needed too with the option to use some of the smaller models (1-3B for example). Also a local API would be nice for my own python experiments.

Is there anything that can tick the boxes? Even if I have to scoot across models for some of the features? I'd prefer more of a desktop client application than a docker container running in the background.

 

I'm watching some retro television and this show is wild! Beauty contests with 16 year-old girls (though at the time, it was legal for 16 yo girls to pose topless for newspapers), old racist comedians from working men's clubs doing their routine, Boney M, English singers from the time, and happy dance routines!

vid

view more: next ›