llama-factory

name	llama-factory
description	Pointer to LLaMA-Factory, a framework for fine-tuning LLMs (WebUI no-code, 100+ models, QLoRA, multimodal). Use to locate the project and its official documentation.
version	1.0.0
author	Orchestra Research
license	MIT
tags	["Fine-Tuning","LLaMA Factory","LLM","WebUI","No-Code","QLoRA","LoRA","Multimodal","HuggingFace","Llama","Qwen","Gemma"]
dependencies	["llmtuner","torch","transformers","datasets","peft","accelerate","gradio"]

Llama-Factory

LLaMA-Factory is a framework for fine-tuning LLMs. It provides a no-code WebUI, supports 100+ models, parameter-efficient methods (LoRA/QLoRA), and multimodal training.

When to use

• Fine-tuning LLMs without writing training code (WebUI)
• LoRA/QLoRA fine-tuning across many model families
• Multimodal fine-tuning

Resources

• GitHub: https://github.com/hiyouga/LLaMA-Factory
• Documentation: https://llamafactory.readthedocs.io