LlamaDuo：LLMOps管線，從服務LLMs無縫遷移至小規模本地LLMs

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

August 24, 2024

作者: Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jing Tang, Sunghun Kim

cs.AI

摘要

雲端專有大型語言模型（LLMs）的廣泛採用帶來了重大挑戰，包括運營依賴性、隱私擔憂和持續網路連接的必要性。在這項工作中，我們引入了一個名為"LlamaDuo"的LLMOps流程，用於從面向服務的LLMs順利遷移知識和能力到更小、本地可管理的模型。這個流程對於確保在遇到運營故障、嚴格的隱私政策或離線需求時服務的連續性至關重要。我們的LlamaDuo包括對一個小語言模型進行微調，使用由後者生成的合成數據集來對服務LLM進行微調。如果微調模型的表現不如預期，則通過進一步使用服務LLM創建的類似數據進行進一步微調來增強它。這種迭代過程確保較小的模型最終能夠在特定下游任務中匹敵甚至超越服務LLM的能力，為在受限環境中管理AI部署提供了實用且可擴展的解決方案。我們進行了與領先的LLMs的廣泛實驗，以展示LlamaDuo在各種下游任務中的效果、適應性和負擔能力。我們的流程實現可在https://github.com/deep-diver/llamaduo 上找到。

English

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 enhanced by further fine-tuning with additional similar data created by the service LLM. This iterative 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.