wolverminion/llama-pro-instruct repository overview

⁠Installation of llama-pro-instruct from ollama.com

⁠Usage

To use this Docker container, simply run the following command in your terminal:

docker run --rm -it wolverminion/llama-pro-instruct:tagname

If you have an nVidia GPU, and it is configured for use by docker containers, llama-pro-instruct can use your GPU, launch as follows:

docker run --gpus all --rm -it wolverminion/llama-pro-instruct:tagname

Replace tagname with the specific tag you want to use.

⁠Description

This all-in-one solution contains and runs the server, and has the cli as its Docker entrypoint. It is an installation of llama-pro from ollama.com.