this post was submitted on 20 Jan 2024
413 points (96.0% liked)

Technology

59433 readers
3973 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 3 points 10 months ago* (last edited 10 months ago) (2 children)
[–] [email protected] 12 points 10 months ago (1 children)

The question is quickly answered as none is currently that good, open or not.

Anyway it seems that this is just a manager. I see some competitors available that I have heard good things about, like mistral.

[–] [email protected] 9 points 10 months ago (2 children)

Local LLMs can beat GPT 3.5 now.

[–] Speculater 5 points 10 months ago (1 children)

I think a good 13B model running on 12GB of VRAM can do pretty well. But I'd be hard pressed to believe anything under 33B would beat 3.5.

[–] [email protected] 4 points 10 months ago* (last edited 10 months ago) (1 children)

Asking as someone who doesn't know anything about any of this:

Does more B mean better?

[–] [email protected] 5 points 10 months ago

B stands for Billion (Parameters) IIRC

[–] june 0 points 10 months ago

3.5 fuckin sucks though. That’s a pretty low bar to set imo.

[–] Falcon 5 points 10 months ago* (last edited 10 months ago) (1 children)

Many are close!

In terms of usability though, they are better.

For example, ask GPT4 for an example of cross site scripting in flask and you'll have an ethics discussion. Grab an uncensored model off HuggingFace you're off to the races

[–] [email protected] 1 points 10 months ago (1 children)

Seems interesting! Do I need high end hardware or can I run them on my old laptop that I use as home server?

[–] Falcon 1 points 10 months ago (2 children)

Oh no you need a 3060 at least :(

Requires cuda. They’re essentially large mathematical equations that solve the probability of the next word.

The equations are derived by trying different combinations of values until one works well. (This is the learning in machine learning). The trick is changing the numbers in a way that gets better each time (see e.g. gradient descent)

[–] ripcord 2 points 10 months ago (1 children)

How's the guy who said he's running off a 1060 doing it?

[–] Chee_Koala 4 points 10 months ago (1 children)
[–] ripcord 2 points 10 months ago

Then you don't need a 3060 at least

[–] [email protected] 1 points 10 months ago

Oh this is unfortunate ahahahaha
Thanks for the info!