arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.13467cs.LGcs.AIcs.DC
收藏

LlamaDuo:用于从服务LLM无缝迁移至小规模本地LLM的LLMOps流水线

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs

Electronics and Telecommunications Research Institute(电子电信研究院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Hugging Face

Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jing Tang

AI总结:

提出LLMOps流水线LlamaDuo,通过服务LLM生成的合成数据集多轮微调小规模本地模型,实现从云端服务LLM到本地小模型的知识与能力无缝迁移,确保在隐私或离线等受限环境下的服务连续性。

摘要:

云端专有大语言模型(LLM)的广泛采用带来了重大挑战,包括操作依赖、隐私担忧以及对持续互联网连接的需求。在本研究中,我们提出了一种LLMOps流水线“LlamaDuo”,用于将知识和能力从面向服务的LLM无缝迁移到较小的、本地可管理的模型。该流水线对于在出现操作故障、严格隐私政策或离线要求时确保服务连续性至关重要。我们的LlamaDuo涉及使用后者生成的合成数据集,针对服务LLM微调一个小语言模型。如果微调模型的性能未达预期,则通过使用服务LLM生成的额外相似数据进行额外微调来自动改进。这种多轮过程确保较小模型最终能够在特定下游任务中匹配甚至超越服务LLM的能力,为在受限环境中管理AI部署提供了实用且可扩展的解决方案。我们使用前沿LLM进行了广泛实验,以展示LlamaDuo在各种下游任务中的有效性、适应性和经济性。我们的流水线实现可在https://github.com/deep-diver/llamaduo获取。

英文摘要:

The widespread adoption of cloud-based proprietary large language models (LLMs) has introduced significant challenges, including operational dependencies, privacy concerns, and the necessity of continuous internet connectivity. In this work, we introduce an LLMOps pipeline, "LlamaDuo", for the seamless migration of knowledge and abilities from service-oriented LLMs to smaller, locally manageable models. This pipeline is crucial for ensuring service continuity in the presence of operational failures, strict privacy policies, or offline requirements. Our LlamaDuo involves fine-tuning a small language model against the service LLM using a synthetic dataset generated by the latter. If the performance of the fine-tuned model falls short of expectations, it is automatically improved through additional fine-tuning using extra similar data generated by the service LLM. This multi-turn process guarantees that the smaller model can eventually match or even surpass the service LLM's capabilities in specific downstream tasks, offering a practical and scalable solution for managing AI deployments in constrained environments. Extensive experiments with leading-edge LLMs are conducted to demonstrate the effectiveness, adaptability, and affordability of LlamaDuo across various downstream tasks. Our pipeline implementation is available at https://github.com/deep-diver/llamaduo.

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。

↑