RECENT ROTATIONS

If you’re building LLMs but have no way to deploy them, are they even useful? In this post, you’ll deploy an LLM into a live production application!

If you want to protect your IP or avoid vendor lock, you may find that building your own LLM is more practical than relying on services like ChatGPT. In this post, you’ll train a custom LLM using your own data!

Move over ChatGPT, here come the Large Language Models (LLMs). More and more companies are incorporating LLMs into their operations. Are you ready? Here’s the guide to how Rotational plans and scopes our LLM projects.

The last few years have marked a shift in industry away from research-oriented machine learning. These days, shipping models early and often is critical, and open source tools like Prefect can speed up the process of operationalizing ML.

2023 was the year of large language models (LLMs) due to services like ChatGPT and Stable Diffusion gaining mainstream attention. In this series, learn about the architecture behind LLMs and how to build your own custom LLM!

Coming off the 2023 “AI hype cycle”, how should business leaders approach 2024? Learn 5 practical AI strategies every business should consider.

Have you ever tried to build a model that can handle new data in real time? We set out to do just that, and discovered that there aren’t a lot of tutorials about training real-time machine learning models, so we made this one!

Real-time data streams are powerful, but sometimes you need to convert the stream into a batch or replay parts of the stream. Here’s how to write customized SQL to more deeply understand and interact with your historic data.

With the rise of LLMs and Retrieval Augmented Generation (RAG), online models have never been more relevant. Here’s how to write some Python code to interpret real-time data and build your own adaptive online model.

One of the first steps in every data science or machine learning project is data ingestion. In this module, you will use Python to create a publisher to ingest real-time data into Ensign.