Institutional Platform for Secure Self-Service Large Language Model Exploration
This work addresses the need for simplified and secure access to cutting-edge AI models for researchers and users at institutions like the University of Kentucky, though it appears incremental as it builds on existing multi-LoRA inference methods.
The paper tackles the problem of making large language models (LLMs) more accessible by introducing a user-friendly platform that efficiently accommodates custom adapters for diverse users and projects, resulting in a system that provides secure LLM services with features like process isolation and end-to-end encryption.
This paper introduces a user-friendly platform developed by the University of Kentucky Center for Applied AI, designed to make large, customized language models (LLMs) more accessible. By capitalizing on recent advancements in multi-LoRA inference, the system efficiently accommodates custom adapters for a diverse range of users and projects. The paper outlines the system's architecture and key features, encompassing dataset curation, model training, secure inference, and text-based feature extraction. We illustrate the establishment of a tenant-aware computational network using agent-based methods, securely utilizing islands of isolated resources as a unified system. The platform strives to deliver secure LLM services, emphasizing process and data isolation, end-to-end encryption, and role-based resource authentication. This contribution aligns with the overarching goal of enabling simplified access to cutting-edge AI models and technology in support of scientific discovery.