• chiisana@lemmy.chiisana.net
      link
      fedilink
      English
      arrow-up
      23
      ·
      3 months ago

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

      • modeler@lemmy.world
        link
        fedilink
        English
        arrow-up
        40
        ·
        edit-2
        3 months ago

        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.

        • cheddar@programming.dev
          link
          fedilink
          English
          arrow-up
          21
          arrow-down
          1
          ·
          3 months ago

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

        • Siegfried@lemmy.world
          link
          fedilink
          English
          arrow-up
          8
          ·
          edit-2
          3 months ago

          At work we habe a small cluster totalling around 4TB of RAM

          It has 4 cooling units, a m3 of PSUs and it must take something like 30 m2 of space

        • 1984@lemmy.today
          link
          fedilink
          English
          arrow-up
          3
          ·
          3 months ago

          Can you run this in a distributed manner, like with kubernetes and lots of smaller machines?

        • obbeel@lemmy.eco.br
          link
          fedilink
          English
          arrow-up
          2
          ·
          3 months ago

          According to huggingface, you can run a 34B model using 22.4GBs of RAM max. That’s a RTX 3090 Ti.

        • Longpork3@lemmy.nz
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          3 months 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.

      • sunzu@kbin.run
        link
        fedilink
        arrow-up
        12
        ·
        3 months ago

        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

          • sunzu@kbin.run
            link
            fedilink
            arrow-up
            3
            ·
            3 months 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

          • bizarroland@fedia.io
            link
            fedilink
            arrow-up
            3
            ·
            3 months ago

            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?

            • BaroqueInMind@lemmy.one
              link
              fedilink
              English
              arrow-up
              2
              ·
              edit-2
              3 months ago

              What’s the bus speed of the RAM? You might run it just fine but still bottlenecked there.

                • BaroqueInMind@lemmy.one
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  edit-2
                  3 months ago

                  With 144Gb of total RAM, you should be able to run any CPU intensive software.

                  The LLMs use GPU vRAM though, so it doesn’t matter how much system RAM you have, since GPU vRAM is what the xformers and tensor scripts prioritize and have been ultimately optimized to use over CPU and RAM.

        • raldone01@lemmy.world
          link
          fedilink
          English
          arrow-up
          3
          arrow-down
          1
          ·
          edit-2
          3 months ago

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

            • raldone01@lemmy.world
              link
              fedilink
              English
              arrow-up
              2
              ·
              edit-2
              3 months ago

              My specs because you asked:

              CPU: Intel(R) Xeon(R) E5-2699 v3 (72) @ 3.60 GHz
              GPU 1: NVIDIA Tesla P40 [Discrete]
              GPU 2: NVIDIA Tesla P40 [Discrete]
              GPU 3: Matrox Electronics Systems Ltd. MGA G200EH
              Memory: 66.75 GiB / 251.75 GiB (27%)
              Swap: 75.50 MiB / 40.00 GiB (0%)
              
                • raldone01@lemmy.world
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  3 months ago

                  Each card has 24GB so 48GB vram total. I use ollama it fills whatever vrams is available on both cards and runs the rest on the CPU cores.

            • raldone01@lemmy.world
              link
              fedilink
              English
              arrow-up
              1
              ·
              3 months ago

              What are you asking exactly?

              What do you want to run? I assume you have a 24GB GPU and 64GB host RAM?

      • Blaster M@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        ·
        3 months 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.

      • 5redie8@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        ·
        3 months ago

        “an order of magnitude” still feels like an understatement LOL

        My 35b models come out at like Morse code speed on my 7800XT, but at least it does work?

    • bitfucker@programming.dev
      link
      fedilink
      English
      arrow-up
      4
      ·
      3 months 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.