• 0 Posts
  • 21 Comments
Joined 1 year ago
cake
Cake day: June 26th, 2023

help-circle






  • Dunno bro everything works for me on mint. I also have higher frame rates and better stability. Getting Stable Diffusion working on my AMD card is probably the hardest thing i have had to do. Even that is three lines in the terminal now. You may need to dick around with proton settings and read the forums to find what Cyberpunk runs on best if you want to deal with the bug.











  • Depends how you get in accomplished if you use the python bindings its slow but using the gpt4all its quick and there is a gpt4all api should you wish to build a private assistant. I like that one but its still run by a company so mileage may vary there are a few projects on github for use with opensource models. I can get better quality from the hermes model than i can with GPT 3.5 IMO but some models are better than others in regards to what you are trying to do. If you have done any work with stable diffusion lots of different models are popping up right now for different use-cases like you see on civit.ai. A good coding bot is probably going to be a bit shit in a conversation.




  • I made the switch to linux that time they had three bad patches in a row and nothing was working. Every issue I have had in an issue in linux I am able to fix myself since nothing is obfuscated. I was using x11 rewritten by some Croatian dude as a proof of concept because it was the only thing that allowed torch to address the video card properly. Run into an issue in windows and find out that neither the manufacturer nor microsoft are supporting your product. Nothing i can do about it. Utterly rage inducing.