Tutorial
QLoRA Explained: Fit a 13B Model on One L4 GPU
QLoRA fits a 13B LLM on one L4 GPU by pairing 4-bit quantization with LoRA adapters. Here's exactly how it works and how to run it yourself.
Tutorial
Notebook to Google Vertex AI Pipeline: MLOps End-to-End
Most ML models die in notebooks. Here's exactly what it takes to get one running on Google Vertex AI Pipelines — from first component to live endpoint.
Tutorial
Build a RAG Chatbot with pgvector and Claude
Week 8 of our NLP & LLM Engineering course ends with students shipping a working RAG chatbot that answers questions over their own PDFs. Here's the full build.
Tutorial
Retrieval Augmented Generation with pgvector: A Production Tutorial
We teach retrieval augmented generation with pgvector in week 7 of NLP & LLM Engineering. Here's exactly what the build looks like.