198
The first GPT-4-class AI model anyone can download has arrived: Llama 405B (arstechnica.com)
submitted 2 years ago by to c/technology@lemmy.world
61 comments fedilink hide all child comments

top 50 comments

sorted by: hot top controversial new old
[–] 97 points 2 years ago (4 children)

Technically correct (tm)

Before you get your hopes up: Anyone can download it, but very few will be able to actually run it.

  • permalink
  • fedilink
  • source
  • hideshow 8 child comments
    •
  • [–] 23 points 2 years ago (3 children)

    What’s the resources requirements for the 405B model? I did some digging but couldn’t find any documentation during my cursory search.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 41 points 2 years ago* (8 children)

    Typically you need about 1GB graphics RAM for each billion parameters (i.e. one byte per parameter). This is a 405B parameter model. Ouch.

    Edit: you can try quantizing it. This reduces the amount of memory required per parameter to 4 bits, 2 bits or even 1 bit. As you reduce the size, the performance of the model can suffer. So in the extreme case you might be able to run this in under 64GB of graphics RAM.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 15 child comments
    •
  • [–] 13 points 2 years ago (2 children)

    Or you could run it via cpu and ram at a much slower rate.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 2 years ago*

    Hmm, I probably have that much distributed across my network... maybe I should look into some way of distributing it across multiple gpu.

    Frak, just counted and I only have 270gb installed. Approx 40gb more if I install some of the deprecated cards in any spare pcie slots i can find.

  • permalink
  • fedilink
  • source
  • parent
    • load more comments (1 reply)
  • [–] 12 points 2 years ago (2 children)

    405b ain't running local unless you got a proepr set up is enterpise grade lol

    I think 70b is possible but I haven't find anyone confirming it yet

    Also would like to know specs on whoever did it

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 8 points 2 years ago* (2 children)

    I've run quantized 70B models on CPU with 32 gigs but it is very slow

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 3 points 2 years ago

    I gonna add some RAM with hope I can split original 70b between GPU and RAM. 8b is great what it is as is

    Looks like it should be possible, not sure how much performance hit offloading to RAM will do. Fafo

  • permalink
  • fedilink
  • source
  • parent
  • [–] 3 points 2 years ago (1 child)

    I have a home server with 140 gigs of RAM, it was surprisingly cheap. It's an HP z6 with the 6146 gold xeon processor.

    I found a seller who was selling it with a low spec silver and 16 gigs of RAM for like 250 bucks.

    Found the processor upgrade for about $120 and spend another $150 on 128gb of second-hand ECC ddr4.

    I think the total cost was something like $700 after throwing a couple of 8 TB hard drives in.

    I've also placed a Nvidia 4070 in it, which I got doing some horse trading.

    How close am I on the specs to being able to run the 70b version?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 2 years ago* (last edited 2 years ago) (1 child)

    I regularly run llama3 70b unqantized on two P40s and CPU at like 7tokens/s. It's usable but not very fast.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 2 years ago (4 children)

    so there is no way a 24gb and 64gb can run thing?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
    • load more comments (3 replies)
  • [–] 6 points 2 years ago

    As a general rule of thumb, you need about 1 GB per 1B parameters, so you're looking at about 405 GB for the full size of the model.

    Quantization can compress it down to 1/2 or 1/4 that, but "makes it stupider" as a result.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 5 points 2 years ago

    So does OSM data. Everyone can download the whole earth but to serve it and provide routing/path planning at scale takes a whole other skill and resources. It's a good thing that they are willing to open source their model in the first place.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 19 points 2 years ago (5 children)

    Wake me up when it works offline "The Llama 3.1 models are available for download through Meta's own website and on Hugging Face. They both require providing contact information and agreeing to a license and an acceptable use policy, which means that Meta can technically legally pull the rug out from under your use of Llama 3.1 or its outputs at any time."

  • permalink
  • fedilink
  • source
  • hideshow 9 child comments
    •
    • load more comments (1 reply)
    [–] 16 points 2 years ago (1 child)

    Yo this is big. In both that it is momentous, and holy shit that’s a lot of parameters. How many GB is this model?? I’d be able to run it if I had an few extra $10k bills lying around to buy the required hardware.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
    • [–] 11 points 2 years ago

    Kind of petty from Zuck not to roll it out in Europe due to the digital services act.. But also kind of weird since it's open source? What's stopping anyone from downloading the model and creating a web ui for Europe users?

  • permalink
  • fedilink
  • source
    •
    [–] 2 points 2 years ago (1 child)

    Did anyone get 70b to run locally?

    If so what, what hardware specs?

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 5 points 2 years ago (1 child)

    Afaik you need about 40GB of vram for a 70b model.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
    • [–] 1 point 2 years ago (1 child)

    That looks good on paper, but while I find ChatGPT good to create critical thinking, I've found Meta's products (Facebook and Instagram) to be sources of disinformation. That makes me have reservations about Meta's intentions with LLMs. As the article says, the model comes pre-trained, so it's most made up of information gathered by Meta.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 2 points 2 years ago

    Neither Meta nor anyone else is hand-curating their dataset. The fact that Facebook is full of grandparents sharing disinformation doesn't impact what's in their model.

    But all LLMs are going to have accuracy issues because they're 1) trained on text written by humans who themselves are inaccurate and 2) designed to choose tokens based on probability rather than any internal logic as to whether an answer is factual.

    All LLMs are full of shit. That doesn't mean they're not fun or even useful in some applications, but you shouldn't trust anything they write.

  • permalink
  • fedilink
  • source
  • parent
    • load more comments
    view more: next ›