LLaMA-Factory

LLaMA-Factory has earned its status as one of the most-starred fine-tuning projects on GitHub by covering an unusually wide surface area in one framework: over 100 base and vision-language models, essentially every parameter-efficient method in current use (LoRA, QLoRA, DoRA, OFT), full fine-tuning, and the full spectrum of alignment techniques from PPO and DPO through KTO, ORPO, and SimPO. Few tools, open or commercial, match that breadth in a single codebase. The Gradio-based LLaMA Board interface is a real differentiator, letting users without deep ML engineering experience configure and launch a fine-tuning run without writing training code, while the CLI and memory-efficient optimizers (GaLore, BAdam, Adam-mini) give power users room to push efficiency further on constrained hardware. Direct support for current model families like Qwen3, DeepSeek, and GLM-4, plus OpenAI-compatible serving via vLLM after training, closes the loop from fine-tune to deployment cleanly. Being Apache 2.0 licensed with no paid tier makes it effectively free infrastructure for teams that would otherwise need custom training scripts. The tradeoff of such a broad, fast-moving project is that documentation and stability can lag new features, so pinning versions is wise for production use.