Pi
Pi
I think the MacOS binaries were built just a day before the Apple ARM64 chip optimization was merged into llama.cpp. If you want, you can send me the new llama.cpp...
> i just sent you the files on discord! :) Thank you.
Ok everyone, i just updated the v1.0.5 macOS ARM64 release. Try downloading and installing it again. It should be faster now.
> Works great! Thanks for the change. Only problem now is > > ``` > bash: Would: command not found > bash-3.2$ > ``` > > After clearing chat, but...
> if your code is not malware then you might want to report it to the MaxSecure. >  Ehhh I'm too lazy to. MaxSecure is probably not gonna do...
> also the npm, install gives >  > Thanks, I'll check that out. But afaik, I'm using the latest packages. Might be wrong though.
I'll add that soon.
Because Powershell is used to run llama.cpp, which is what powers Alpaca Electron. The AI can't possibly do any harm to your computer.
I added it a while back. But I guess duck-duck-scrape broke or smth. Because it doesn't work anymore. I'll have a look when I have time.
Defaulting to CPU thread count isnt always the best. 1. It should be a power of 2 or multiple of 8. 16 threads will perform better than 18. 2. It...