Jonathan Yankovich

+1, if this existed, I would run it on Unraid as well.

If it's possible to add a separate file that can be invoked to do CLI training, i would love that. I am currently attempting to run training via CLI; I...

Note that has a supported build of Tasmota for ESP32 / ESPCAM, and it provides HTTP and RTSP out of the box. It can also change resolution using the inbuilt...

Very much looking forward to docker support!

hmph

If I click a link to another website, I generally think its going to open in a tab. For internal links, I don't expect that. I can see that going...

And there's always https://github.com/KoboldAI/KoboldAI-Client/ which probably won't get FlexGen support for some time.

Does anyone know, is it possible to run multiple instance of this dockerfile using a single GPU? I'm not able to run multiple instances from bash; when I try, the...

Here's a potentially useful page I found that describes steps for running Kobold AI in 8-bit mode: https://gist.github.com/whjms/2505ef082a656e7a80a3f663c16f4277

Another interesting development that is worth looking into - int4 and int8, supports multi-gpu, splitting gpu/cpu ram, etc: https://github.com/FMInference/FlexGen I am wondering if these 4/8 bit models would run well...