ohmplatform / FreedomGPT

This codebase is for a React and Electron-based app that executes the FreedomGPT LLM locally (offline and private) on Mac and Windows using a chat-based interface

FreedomGPT

This is the offical repository for the FreedomGPT application. It is built using Electron and React and allows users to run LLM models on their local machine.

Join our Discord Community

Join our Discord server to get the latest updates and to interact with the community.

How to Contribute

Prerequisites

• Node.js
• Git

Quick Install

git clone --recursive https://github.com/ohmplatform/FreedomGPT.git freedom-gpt
cd freedom-gpt
npx yarn install

Building the llama.cpp library

macOS

cd llama.cpp
make

Windows

• Download and install CMake: https://cmake.org/download/
• Run the following commands:

cd llama.cpp
cmake .
cmake --build . --config Release

You should now have a Release folder with a main.exe file inside it. You can run this file to test the chat client.

Running the App

To run the app, run the following command in your terminal from the root directory of the project:

npx yarn start

Changing Ports

If needed, ports can be changed in: src/ports.ts

Installation and Setup Guide for Linux

Required Packages

To get started, you need to install several required packages. Run the following commands:

sudo apt install nodejs
sudo apt install yarn
sudo apt install git
sudo apt install make
sudo apt install g++
sudo apt install npm

Build the Project

Navigate to the project directory and build it:

cd freedom-gpt/llama.cpp
make
cd ..
npm install
npm run
npm start

Usage

Working with Liberty Edge Models

You can manually download the Liberty Edge models and set the paths to these files from the AI Models screen.

Mining Earnings

To enable mining earnings, follow these steps:

1. Download the XMRig Linux Static, CPU-only version from xmrig.com/download
2. Extract the archive and copy the xmrig binary to the freedom-gpt/miner/mac/fgptminer directory:

# Assuming you have extracted xmrig in the current directory
cp xmrig freedom-gpt/miner/mac/fgptminer

Credits

This project utilizes several open-source packages and libraries, without which this project would not have been possible:

"llama.cpp" - C++ library. https://github.com/ggerganov/llama.cpp

"LLAMA" by Facebook Research - a low-latency, large-scale approximate nearest neighbor search algorithm. https://github.com/facebookresearch/llama

"Chatbot UI" - https://github.com/mckaywrigley/chatbot-ui

We would like to express our gratitude to the developers of these packages and their contributors for making their work available to the public under open source licenses. Their contributions have enabled us to build a more robust and efficient project.

LICENSE

See the LICENSE file.