lxe/simple-llm-finetuner

A beginner-friendly UI for fine-tuning language models using LoRA on commodity NVIDIA GPUs, though the project is no longer actively maintained.

Core Features

Intuitive UI for dataset input and management

Adjustable parameters for fine-tuning and inference

Beginner-friendly explanations for each parameter

Supports LoRA method via PEFT library

Integrated model inference capabilities post-training

GitHub Repo Full Preview

Quick Start

python app.py

Detailed Introduction

Simple LLM Finetuner was an intuitive, beginner-friendly interface designed to simplify the fine-tuning of various language models using the LoRA method via the PEFT library on commodity NVIDIA GPUs. It offered a UI for dataset management, parameter customization, training, and inference evaluation. However, the project is now effectively dead, and users are advised to explore alternative tools like LLaMA-Factory, Unsloth, or text-generation-webui for similar functionalities.