dblacknc

The object storage (S3) server is a third-party vendor (not MinIO) that I don't feel free to specify in this forum, sorry. With this same vendor a wide variety of...

The --threads option says it only pertains to llama.cpp, and best I know it runs (only) the GGML CPU-only models. In that mode I've seen it use all of 16...

Instruct, with the Open Assistant template selected. To make sure I was clear - it will respond normally then seemingly randomly start responding to itself for a round or two....

That seems to take care of it, thanks! Good thing too, because without, it also did this: The cube root of 123, when rounded to two decimal places, is approximately...

I noticed this last night when clicking "Continue" after generation stopped at the token limit. I'm not sure the space insertion was always there, like this may be a recent...

It has worked well for me all along, including today after a git pull. OS is Ubuntu 22.04. A firewall could block access from the LAN, while allowing localhost to...

On either Windows or Linux, you could try "netstat -a -n" to verify what address a socket is bound to. I'm using --listen --listen-port 80. For your netstat -a -n...

I haven't yet tried any of the workarounds, but recently hit this too: With --monkey-patch, --auto-devices or --pre_layer no longer seem to work - at least to run across GPUs....

It worked when specifying GPU memory, thanks.

If I have neither --auto-devices nor --load-in-8bit on the command line, it'll load until it runs out of VRAM on my first 12 GB GPU. Looks like it needs around...