This is how I got https://github.com/facebookresearch/llama working with Llama2 on a Windows 11 machine with a 4080 (16GB VRAM).
- Download a modern version of wget (with support for TLS 1.2) - ie. https://eternallybored.org/misc/wget/
- (if necessary) Modify
download.sh
to call your version ofwget
instead of the default one. - Run
./download.sh
via Git Bash and give it the URL from your email (it should start withhttps://download.llamameta.net
, nothttps://l.facebook.com/
). Warning: the 70B parameter models are big - figure 2GB to download per 1B parameters. - Create a virtual environment -
python -m venv .venv
- Activate virtual environment -
. .\.venv\scripts\Activate.ps1
- Install prereqs -
pip install -r requirements.txt