logoalt Hacker News

simonwtoday at 5:53 PM3 repliesview on HN

If it's part of their training set why do the 2B and 4B models produce such terrible SVGs?


Replies

vessenestoday at 6:23 PM

We were promised full SVG zoos, Simon. I want to see SVG pangolins please

wolttamtoday at 8:39 PM

Because it is in their training set but it's unrealistic to expect a 2B or 4B model to be able to perfectly reproduce everything it's seen before.

The training no doubt contributed to their ability to (very) loosely approximate an SVG of pelican on a bicycle, though.

Frankly I'm impressed

retinarostoday at 8:05 PM

because generating nice looking svg requires handling code, shapes, long context, reasoning and at 2b you most likely will break the syntax of the file 9 times out of 10 if you train for that. or you will need to go for simpler pelicans. might not be worth to ft on a 2b. but on their top tier open model it is definitly worth it. even not directly but just crawling a github would make it train on your pelicans.