←back to thread

Ask HN: Is anyone doing anything cool with tiny language models?

684 points prettyblocks | 1 comments | 21 Jan 25 19:39 UTC | HN request time: 0.211s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
1. jwitthuhn ◴[22 Jan 25 01:45 UTC] No.42787767[source]▶
I've made a tiny ~1m parameter model that can generate random Magic the Gathering cards that is largely based on Karpathy's nanogpt with a few more features added on top.

I don't have a pre-trained model to share but you can make one yourself from the git repo, assuming you have an apple silicon mac.

https://github.com/jlwitthuhn/TCGGPT