Skip to content

Instantly share code, notes, and snippets.

@peteristhegreat

peteristhegreat/llama-cpp-basic-usage.md

Created July 5, 2023 13:55
Show Gist options
  • Save peteristhegreat/57bc423e76694a512d3722fb17cd126a to your computer and use it in GitHub Desktop.
Save peteristhegreat/57bc423e76694a512d3722fb17cd126a to your computer and use it in GitHub Desktop.
Download ZIP
llama.cpp notes
Raw
llama-cpp-basic-usage.md

https://news.ycombinator.com/item?id=35937505

https://gist.github.com/rain-1/8cc12b4b334052a21af8029aa9c4fafc

curl micro.mamba.pm/install.sh | bash

Cuda install for WSL + Ubuntu:

https://developer.nvidia.com/cuda-downloads?target_os=Linux&target_arch=x86_64&Distribution=WSL-Ubuntu&target_version=2.0&target_type=deb_local

https://huggingface.co/vicuna/ggml-vicuna-7b-1.1

git checkout 08737ef720f0510c7ec2aa84d7f70c691073c35d
make clean

alias ai="cd $HOME/src/llama.cpp; script -c './run.sh' -a airecord.script; echo 'Done recording'"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment