I consolidated my setup a bit. This is my local LLM hosting server. I took a gamble on a Chinese NVLink SXM2 mezzanine board from ebay, it was surprisingly plug and play for my dual 16GB v100s 😂. I’m also running a Tesla P40 that I repasted with liquid metal that sits at 24C idle 🥶.
I had a similar goal with Hermes, but ended up splitting the context between separate profiles instead of teaching one agent everything. They share a Kanban board, while important decisions still come back to me.
It may be overkill for a homelab, but the profile isolation has worked better than I expected. I documented the setup here: https://github.com/nohuman-labs/agent-company
That’s great! But I’m even more curious about the green device in the background of the first pic 👀 What’s that?
It’s an older version of a heatset insert fixture. I used it to put threaded brass inserts into my 3d prints instead of trying to capture a nut or screwing directly into plastic.
https://www.printables.com/model/609644-stealth-press-1-heat-set-insert-press-legacy
That’s interesting. Thanks!
What kind of model and space limitations are you under with v100s?
Some of the most interesting computer music I’ve heard in years was composed on them but idk if it’s worth getting into a whole new generation of hardware if it can only really do that.
This looks amazing. Did you make it with a CNC machine? Are you planning to add an enclosure? I think it would look even better with one.
From the first photo I thought this was an earthquake simulator with models of skyscrapers
Nice, dude. Love anyone who learns by doing.
It’s been a fascinating experience so far and I feel like I’m only touching the surface. I’m exploring some of the various memory harnesses to hook into Hermes Agent and see how it learns with extended use.