this post was submitted on 07 Feb 2024
196 points (95.4% liked)

Technology

59020 readers
3508 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
 

Abacus.ai:

We recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to have an average score more than 80.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 16 points 8 months ago (2 children)

Oh if only it were so simple lmao, you need ~130GB of VRAM, aka the graphics card RAM. So you would need about 9 consumer grade 16GB graphics cards and you'll probably need Nvidia because of fucking CUDA so we're talking about thousands of dollars. Probably approaching 10k

Ofc you can get cards with more VRAM per card, but not in the consumer segment so even more $$$$$$

[–] [email protected] 9 points 8 months ago (1 children)

Afaik you can substitute VRAM with RAM at the cost of speed. Not exactly sure how that speed loss correlates to the sheer size of these models, though. I have to imagine it would run insanely slow on a CPU.

[–] [email protected] 7 points 8 months ago* (last edited 8 months ago)

I tested it with a 16GB model and barely got 1 token per second. I don't want to imagine what it would take if I used 16GB of swap instead, let alone 130GB.

[–] [email protected] 0 points 8 months ago (1 children)

I'm pretty sure you can load the model using RAM like another poster said. Here's a used server under $600 that could theoretically run it: ebay.

[–] [email protected] 5 points 8 months ago

You would want to look for an R730, which can be had for not too much more. The 20 series was the “end of an era” and the 30 series was the beginning of the next era. Most importantly for this application, R30s use DDR4 whereas R20s use DDR3.

RAM speed matters a lot for ML applications and DDR4 is about 2x as fast as DDR3 in all relevant measurements.

If you’re going to offload any part of these models to CPU, which you 99.99% will have to do for a model of this size with this class of hardware, skip the 20s and go to the 30s.