llama.go
llama.go copied to clipboard
feat: interactive mode for a chatgpt like experience
trafficstars
Just wanted to create an issue to track this, I am going to implement it in a different branch and will submit a PR when it's usable.
Great! I've fixed a bit of your latest addition with Ring container, will wait for interactive mode :)
I'm going to investigate some other things like AVX intrinsics and mmap() for faster model loading.