Script to run Llama2 models - CPU only
1 - log into linux 2 - make sure that python is installed 3 - create and activate python environment python -m venv [name of environment] source [name of environment]/bin/activate 4 - pip install llama-cpp-python pip install langchain-community 5 - git clone [this repo link] 6 - create new directory and download model into it mkdir llama wget [download link] 7 - edit model path on python file 8 - on the directory with the python llama_cpu.py run the file python llama_cpu.py