this post was submitted on 23 Jul 2024
75 points (89.5% liked)

Technology

60052 readers
2851 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 2 years ago
MODERATORS
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
75
Llama 3.1 AI Models Have Officially Released (llama.meta.com)
submitted 5 months ago by [email protected] to c/[email protected]
22 comments fedilink hide all child comments
 

Big day for people who use AI locally. According to benchmarks this is a big step forward to free, small LLMs.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 1 points 5 months ago (1 children)

Ah, that's a wonderful use case. One of my favourite models has a storytelling lora applied to it, maybe that would be useful to you too?

At any rate, if you'd end up publishing your model, I'd love to hear about it.

[–] [email protected] 2 points 5 months ago (1 children)

[Oh, my friend, you have to switch to this: https://huggingface.co/BeaverAI/mistral-doryV2-12b

It's so much smarter than llama 13B. And it goes all the way out to 128K!

[–] [email protected] 1 points 5 months ago (1 children)

Oof - not on my 12gb 3060 it doesn't :/ Even at 48k context and the Q4_K quantization, it's ollama its doing a lot of offloading to the cpu. What kind of hardware are you running it on?

[–] [email protected] 2 points 5 months ago* (last edited 5 months ago)

A 3090.

But it should be fine on a 3060, with zero offloading.

Dump ollama for long context. Grab a 5-6bpw exl2 quantization and load it with Q4 or Q6 cache depending on how much context you want. I personally use EXUI, but text-gen-webui and tabbyapi (with some other frontend) will also load them.