Welcome to the comprehensive documentation for ModelForge v3 - A no-code toolkit for fine-tuning Large Language Models on your local GPU.
- Quick Start Guide - Get up and running in 5 minutes
- What's New in v3 - Major features and improvements
- Windows Installation - Complete setup guide for Windows users
- Native Windows setup and limitations
- WSL setup for full feature support
- Docker with NVIDIA Container Toolkit
- Linux Installation - Setup guide for Linux
- macOS (Apple Silicon) Installation - Setup for M1/M2/M3/M4/M5 Macs with MPS support
- Post-Installation Setup - Initial configuration steps
- Configuration Guide - Detailed configuration options
- Dataset Formats - Preparing your training data
- Training Tasks - Text generation, summarization, Q&A
- Hardware Profiles - Optimizing for your GPU
- Provider Overview - Understanding model providers
- HuggingFace Provider - Standard HuggingFace models
- Unsloth Provider - 2x faster training with Unsloth
- Adding Custom Providers - Extend with new providers
- Strategy Overview - Understanding training strategies
- Supervised Fine-Tuning (SFT) - Standard LoRA fine-tuning
- QLoRA Strategy - Memory-efficient quantized training
- RLHF Strategy - Reinforcement Learning from Human Feedback
- DPO Strategy - Direct Preference Optimization
- Adding Custom Strategies - Extend with new strategies
- REST API Documentation - Complete API endpoints
- Training Configuration Schema - Configuration options
- Response Formats - API response structures
- Common Issues - Frequently encountered problems
- Windows-Specific Issues - Windows troubleshooting
- FAQ - Frequently asked questions
- Performance Optimization - Getting the best performance
- Contributing Guide - How to contribute
- Development Setup - Setting up development environment
- Architecture Overview - Understanding the codebase
- Model Configurations - Adding model recommendations
- Quick Start - Start here if you're new to ModelForge
- Windows Setup - Essential for Windows users
- Configuration Guide - Learn all configuration options
- Troubleshooting - Having problems? Check here first
- Check the FAQ for quick answers
- Search existing issues on GitHub
- Ask a question in Discussions
- Report bugs via GitHub Issues
ModelForge v3 - Making LLM fine-tuning accessible to everyone.