ludiusvox/AI-companion-from-LM-Studio-into-VS-Code-Codium-IDE

Description

This project seeks to use an NVIDIA GPU accelerated LLM using NVIDIA proprietary or MIT drivers, as well as leveraging the use of a Language Model, directly into the Codium IDE or VS-Code.

Installation Instructions

install fedora drivers for NVIDIA Card:

https://copr.fedorainfracloud.org/coprs/g/ai-ml/nvidia-container-toolkit/

Select your video card and try to install, there may be some other libraries that the installation medium requires.
Check and advise from error logs to install drivers

https://www.nvidia.com/en-us/drivers/

(Tested Version 550.107.02 - x64_86)

LM Studio AppImage

https://lmstudio.ai/

OR

https://files.lmstudio.ai/linux/0.2.31/beta/LM_Studio-0.2.31.AppImage

To activate appimage sudo chmod +x LM_Studio-0.2.31.AppImage ./LM_Studio-0.2.31.AppImage

This is a self updating executable that contains all open source binaries required to run the program LM Studio

Download a usable model (Preferred Mistral8x7B, Meta Llama 3.1-8B)

Setup a Web Server http://localhost:1234

https://marketplace.visualstudio.com/items?itemName=chris-hayes.chatgpt-reborn

Screenshots will be included

Active Releases

The following unofficial repositories are provided as-is by owner of this project. Contact the owner directly for bugs or issues (IE: not bugzilla).

Release	Architectures	Repo Download
Fedora 40	x86_64 (0)*	Fedora 40 (10 downloads)

* Total number of downloaded packages.