Hacker News new | ask | show | jobs
by me-vs-cat 38 days ago
From https://swipe.futo.tech/:

The ContextLM model is a very small language model that is trained for a single language. It's used to improve the quality of predictions by eliminating nonsensical words given the preceding words in the sentence. It only requires text data for training.

1 comments

So it would need one model per language? Not impossible (for me)...