How to setup your own ChatGPT with OpenLLaMA

#ia #llm #chatgpt #opensource

Do you want to have your own ChatGPT? Do you care about privacy? You don't want to pay for the premium version? or you want to use uncensored models. Or even train a model with your company documents.

For these reasons it is a good idea to set up your own LLM model server.

This is an example:

What is OpenLLaMA?
LLama 2 is an LLM (Large Language Model Meta AI)
LLama Meta

What do we need?

Install OpenLLAMA, OpenWebUI and Docker

Installing Ollama

Ollama have support for Windows, Linux and Mac
I recommend minimum 16Gb of RAM.
https://ollama.com/download

For linux setup



curl -fsSL https://ollama.com/install.sh | sh

Download models



ollama pull llama2-uncensored

Run model



ollama run llama2-uncensored

Install Open Web UI

Before install OpenWebUI we need to have installed Docker and running.



docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name open-webui --restart always ghcr.io/open-webui/open-webui:main