I've used https://github.com/PromtEngineer/localGPT for this and thought it was nice. So I packaged it in a docker container for easy use. docker run -itd --gpus all -p $(PORT):5111 --name llm-local-wizardlm-7b…
I've used https://github.com/PromtEngineer/localGPT for this and thought it was nice. So I packaged it in a docker container for easy use. docker run -itd --gpus all -p $(PORT):5111 --name llm-local-wizardlm-7b…