Large Language Models with MLX
Check the repo: 🔗 Large Language Models with MLX.

Check the repo: 🔗 Large Language Models with MLX.

A deep dive into building a local-first retrieval-augmented generation system for document Q&A.
I implemented LoRA and DoRA from scratch in PyTorch to understand the methods end to end.
I explored chat tooling on Apple Silicon using MLX to understand the runtime and packaging story.