Run the Llama 3 model (8-B or 70B) on your server / computer.
- Clone the repository:
git clone https://github.com/IoTtalk/pcs_llama3.git
cd llama3_local
- Install required dependencies:
pip install -r requirements.txt
notify that python3.12 cannot be used.
python llama3_local.py
If you want to setup in a linux server for long term using, you are suggested to use tmux to run code.