cooperdk
cooperdk
I am pretty sure you need to write in English here.
> Faster CPU/GPU for trying it out before buying a decent ML machine? Yeah, no. The binary behind (alpaca) does not support GPU at all so your own computer would...
There is no need for any uncensoring.
Try running the chat command from either resources\models\windows or resources/models/mac in a terminal, point it to the location of the AI model which is in your user profile folder under...
> I saw that it's using the cpu only which is slower. Can you implement a way to choose if the user wants to use cpu or gpu? Unfortunately, chat.exe...
In Windows, the model is downloaded to %USERPROFILE%\FreedomGPT. I imagine it is downloaded to ~/FreedomGPT in Linux. It also stores cache data in %APPDATA%\freedomgpt For ease of use, you might...
> https://github.com/openai/triton#compatibility Only supports Linux. (Or WSL2, but not guaranteed) But someone did make it work: pip install https://huggingface.co/r4ziel/xformers_pre_built/resolve/main/triton-2.0.0-cp310-cp310-win_amd64.whl
I just determined that using Image.antialias makes imagehash NOT produce the same phash values as goimagehash in many cases. With Image.bilinear the values are mostly the same. I have one...
OK, I just requested access.
> I believe the penetrable selection routine itself is bugged, however, fertilization via any means is intended. Marking as a bug so I remember to investigate how penetrables are selected....