Hacker News new | ask | show | jobs
by swaminarayan 84 days ago
How did you make a very small AI model (14M) sound more natural and expressive than even bigger models?
1 comments

glad you liked it, thank you so much for the kind words. our team is really good at squeezing performance out of small models. we are working on a new launch and hope to release a technical report along with that which includes details. fyi, our current 14M model is better than our previous 80M model. and we expect this trend to continue.