Comment on
Discovering Locally Run Language Models: Share Your Favorites/Not So Favorites!
I've been doing RP with Wizard-Vicuna 13b Uncensored. it's good, very fast (ggml v3 q5-k-s variant) But sometimes forgets it's roleplaying and spits out a story
Comment on
llama.cpp for GPU only
Reply in thread
Personally, I have nothing but issues with Oogas ui, so I connect Silly Tavern to it or KoboldCPP. Works great
Comment on
Discord bot connection?
Reply in thread
I'll give it a whirl, thanks. I saw it a day or two ago, but it doesn't really explain how to get it working. May as well try
