How I ended up fine-tuning a language model

Fine-tuning a language model for your own purposes is easier than it has ever been. The technical side is a couple of hours of understanding and a few minutes of compute. While your friendly neighborhood agent handles most of the process, it needs some babysitting and course corrections. Agents won’t solve some of the meatier parts, however. Knowing what you’re trying to make, and being able to tell whether you got there. Both are design problems. Nobody makes small models any more murmur is a haiku generator with a t-shirt shop attached. You type a situation, a small language model writes you a haiku, and you can put it on a shirt. The model runs in your browser rather than on a server, so it runs locally, does no data-center inference, and has a relatively small download. I started the next iterations, since the haikus weren’t interesting or diverse enough. My assumption was that some time had passed, so there was probably a newer and better model, and while I was in there I could…