Juan Montalvo Bressi juan-m12i

Context for PR changes

Create a GPU instance (I am using an L4 GPU, with >100 GB hard drive, and 8vcpu, based on Debian 11)
Enable a firewall rule for ingress on port 8888
Connect through ssh to the instance and run the commands below

sudo apt update
sudo apt -y install build-essential
sudo apt install -y linux-headers-$(uname -r)

Note: I'm currently taking a break from this course to focus on my studies so I can finally graduate

	# mostly from https://kubito.dev/posts/llama-cpp-linux-nvidia/
	# Define the model path as a variable
	MODEL_PATH="models/mistral-7B-v0.1"

	# Rest of your shell script
	git clone https://github.com/ggerganov/llama.cpp
	cd llama.cpp

	# add nvcc to path
	echo 'export PATH=/usr/local/cuda/bin:$PATH' >> ~/.zshrc

	# https://docs.privategpt.dev/installation
	git clone https://github.com/imartinez/privateGPT
	cd privateGPT

	curl https://pyenv.run \| bash

	# echo -e '\nexport PYENV_ROOT="$HOME/.pyenv"\n[[ -d $PYENV_ROOT/bin ]] && export PATH="$PYENV_ROOT/bin:$PATH"\neval "$(pyenv init -)"\neval "$(pyenv virtualenv-init -)"' >> ~/.zshrc
	echo 'export PYENV_ROOT="$HOME/.pyenv"' >> ~/.zshrc && echo 'export PATH="$PYENV_ROOT/bin:$PATH"' >> ~/.zshrc && echo 'eval "$(pyenv init -)"' >> ~/.zshrc && echo 'eval "$(pyenv virtualenv-init -)"' >> ~/.zshrc
	source ~/.zshrc