Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The model is gigabytes so I doubt they will push updates frequently.


Educate me: is there any work on modifying models in a way that changes relatively few parameters, so an update is a smaller payload?


Yeah, LoRAs. Apple uses them to specialize a single model for different uses.


Thanks! Very interesting. Lead inventor Edward Hu describes them, and their usage, incredibly well in this video:

https://youtu.be/DhRoTONcyZE?si=vM2N5zNslbQ5z8gv




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: