Intermediate
Local LLMs: run models on your own hardware
Run language models on your own hardware, no API and no quotas: from Ollama to serving big models on a Mac, plus vector memory for RAG.
Learning paths
Guided paths through the best of the archive: from first step to mastery, in order.
Run language models on your own hardware, no API and no quotas: from Ollama to serving big models on a Mac, plus vector memory for RAG.
The activation functions that let a neural network learn, from the simplest to the most used — with formulas, derivatives and plots.
From zero to your own server: install Docker, manage containers, then add a reverse proxy, authentication and security — every step tested.