Hacker News new | ask | show | jobs
by dvfjsdhgfv 12 days ago
> This will break the rigid instruction-tuning structure

Well, this is something one might naively hope for, unfortunately it only works to a certain extent.

1 comments

Can you elaborate? Where does the structure come from in this case? The model can't even see the boundaries of the reply (it's started with a prefill and stopped with a custom stopping string).