§ MODULE 01 / FOUNDATIONS90 min
LLM Playground on Local Hardware
Train a tiny GPT, then sample it every way
Build: Train a tiny GPT from scratch on your own GPU, then benchmark four decoding strategies.
Proof: A decoding-strategy benchmark table, quality vs tokens/sec on your card.
Connecting sign-in... If this never resolves, sign-in is misconfigured or blocked. Email pat@bmdpat.com and mention the course.