Part 2 of a 4-part series. How LoRA works (the low-rank trick), a working PEFT config, and three real GPU walls I hit — the FP16 unscale error, an OOM, and a 2-GPU speed mystery.
LoRA: I Trained
Related
I Built a Free API That Detects Phishing Sites Using AI Vision - And It Catches Prompt Injection Too
Most phishing detection APIs check URL reputation databases. The problem? Brand new phishing sites...
Notes: Memory, Context, and Large Language Models (LLMs)
Notes following a discussion on how memory works in language models - and how it could be improved:...
I gave a brand-new AI the memory of all my old chats, here's the free tool I built to do it.
My AI conversations were scattered across three apps that couldn't remember each other. So I built a...