Moritz Bauer
Moritz Bauer is a Senior Data Scientist at Blue Yonder, where he currently develops software for demand forecasting. In a previous career, he obtained a Ph.D. in high-energy particle physics and contributed research to the Belle II flavor physics experiment at KEK.
While demand forecasting works very well without language models, he can't escape the fascination of modern AI and is always looking for excuses to spend some time in this domain.
Session
Command Line Interfaces (CLIs) offer an efficient and powerful way to interact with software, but poorly designed interfaces can be incredibly frustrating. Complicated parameter names and unconventional formats can turn using a great tool into a burdensome experience.
Large Language Models (LLMs) seem like a great solution to this problem as they can easily add a natural-language interface to any CLI. However, LLMs can introduce their own challenges, such as requiring API keys or high-performance GPUs. In this talk, I'll demonstrate a method for creating natural-language interfaces for any CLI using fine-tuned Small Language Models. These models are lightweight enough to be run directly on laptops or even smartphones.
We'll explore the process of generating synthetic data, fine-tuning models, and evaluating their performance using both an in-house CLI and a well-known open-source package as examples.