• 0 Posts
  • 10 Comments
Joined 1 year ago
cake
Cake day: December 7th, 2023

help-circle



  • I can only speak for myself here but… A lot of things are taught in school. Most of them weren’t something that I use everyday and thus have forgotten about it (some more than others, of course).

    Ohm’s Law would’ve been taught to me sometime during highschool (as the other commenter mentioned, I can tell you it relates to electricity but without looking it up I couldn’t tell you the actual principle behind it) - I graduated from highschool 10 years ago, and have not had a reason to “flex” that memory ever since then.





  • Hmm, gotcha. I just tried out a fresh copy of text-gen-webui and it seems like the latest version is borked with ROCM (I get the CUDA error: invalid device function error).

    My next recommendation then would be LM Studio which to my knowledge can still output an OpenAI compatible API endpoint to be used in SillyTavern - I’ve used it in the past before and I didn’t even need to run it within Distrobox (I have all of the ROCM stuff installed locally, but I generally run most of the AI stuff in distrobox since it tends to require an older version of Python than Arch is currently using) - it seems they’ve recently started supporting running GGUF models via Vulkan, which I assume probably doesn’t require the ROCM stuff to be installed perhaps?

    Might be worth a shot, I just downloaded the latest version (the UI has definitely changed a bit since I last used it) and just grabbed a copy of the Gemma model and ran it, and it seemed to work without an issue for me directly on the host.

    The advanced configuration settings no longer seem to directly mention GPU acceleration like it used to, however I can see it utilizing GPU resources in nvtop currently, and the speed it was generating at (the one in my screenshot was 83 tokens a second) couldn’t have possibly been done on the CPU so it seems to be fine on my side.