面向指令跟随大语言模型的中文指令数据上全参数微调与基于LoRA微调的对比研究
A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
AI总结：
本文以LLaMA为基座，在中文指令数据上对比全参数微调与LoRA微调，分析基座模型、数据规模、可学习参数量和训练成本对性能的影响，为中文大模型训练提供成本与性能权衡参考。
摘要：
近年来，大语言模型的指令微调是自然语言处理领域中的一个关键研究方向。由于资源和成本限制，一些研究者采用参数高效微调技术（如LoRA）进行指令微调，并取得了令人鼓舞的结果。与全参数微调相比，基于LoRA的微调在训练成本方面表现出显著优势。在本研究中，我们以LLaMA作为基础模型，对全参数微调和基于LoRA的微调方法进行了实验比较。实验结果表明，基础模型的选择、训练数据集规模、可学习参数数量以及模型训练成本都是重要因素。我们希望本文的实验结论能够为大语言模型训练（尤其是中文领域）提供启发，并帮助研究者在训练成本与模型性能之间找到更好的权衡策略。为便于复现本文结果，数据集、模型和代码将被公开。
英文摘要：
Recently, the instruction-tuning of large language models is a crucial area of research in the field of natural language processing. Due to resource and cost limitations, several researchers have employed parameter-efficient tuning techniques, such as LoRA, for instruction tuning, and have obtained encouraging results In comparison to full-parameter fine-tuning, LoRA-based tuning demonstrates salient benefits in terms of training costs. In this study, we undertook experimental comparisons between full-parameter fine-tuning and LoRA-based tuning methods, utilizing LLaMA as the base model. The experimental results show that the selection of the foundational model, training dataset scale, learnable parameter quantity, and model training cost are all important factors. We hope that the experimental conclusions of this paper can provide inspiration for training large language models, especially in the field of Chinese, and help researchers find a better trade-off strategy between training cost and model performance. To facilitate the reproduction of the paper's results, the dataset, model and code will be released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
