Hacker News new | past | comments | ask | show | jobs | submit login

I've used BERT in a number of production apps, it feels like a very apples to oranges comparison given how the AI landscape has changed since BERT's release.



Then looks like you know already where smaller and weaker models are useful.


What did you use BERT for? Maybe 7B models are up to the task?




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

Search: