LlamaFactory：統一高效微調100多種語言模型

LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

March 20, 2024

作者: Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo

cs.AI

摘要

有效的微調對於調整大型語言模型（LLMs）以適應下游任務至關重要。然而，在不同模型上實施這些方法需要不少努力。我們提出了LlamaFactory，這是一個統一的框架，整合了一套尖端的高效訓練方法。它允許用戶通過內置的Web UI LlamaBoard 靈活地自定義超過100個LLMs的微調，無需編碼。我們在語言建模和文本生成任務上實證了我們框架的效率和有效性。該框架已在https://github.com/hiyouga/LLaMA-Factory 上發布，並已獲得超過13,000顆星和1,600個分支。

English

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 allows users to flexibly customize 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 already received over 13,000 stars and 1,600 forks.