The LLM Factory, developed by the University of Kentucky’s Center for Applied AI, allows users to securely fine-tune their own Large Language Models (LLMs) and query the model on a platform controlled by the University of Kentucky. LLM Factory offers users control, flexibility, and security.
Fine-tuning a model using LLM Factory enables users to develop specialized LLMs tailored to specific projects. With this platform, users can upload their own datasets, train models by layering data on a base model, privately configure and explore models, and expose models to external, OpenAI compatible API. For those concerned about the security of private data, LLM Factory offers a solution. Use LLM Factory as an alternative to public models and keep your data secure.
Use the API feature to embed the model (either the fine-tuned model or the base model) into your projects. LLM Factory’s base model is currently Meta LLaMA 3 8B (as of April 2024).
Interact with the chatbot here: https://hub.ai.uky.edu/llm-chat/