LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
This provides a practical tool for researchers and practitioners to streamline fine-tuning of LLMs, though it is incremental as it integrates existing methods into a user-friendly framework.
The paper tackles the problem of implementing efficient fine-tuning methods across diverse large language models by introducing LlamaFactory, a unified framework with a web UI that enables customization for 100+ models without coding, achieving over 25,000 stars and 3,000 forks on GitHub.
Efficient fine-tuning is vital for adapting large language models (LLMs) to downstream tasks. However, it requires non-trivial efforts to implement these methods on different models. We present LlamaFactory, a unified framework that integrates a suite of cutting-edge efficient training methods. It provides a solution for flexibly customizing the fine-tuning of 100+ LLMs without the need for coding through the built-in web UI LlamaBoard. We empirically validate the efficiency and effectiveness of our framework on language modeling and text generation tasks. It has been released at https://github.com/hiyouga/LLaMA-Factory and received over 25,000 stars and 3,000 forks.