top | item 35294087

(no title)

michaelhartm | 2 years ago

Btw, it's kinda crazy how bad the GPT4-J results in the blog are compared to the Dolly one, which seem pretty good. Do we know why it works so well to use this 50k dataset?

discuss

order

quadrature|2 years ago

Dolly is instruction fine tuned whereas GPT4-J is not. Which means that it doesn't even understand that it is being instructed to do something, it is just doing an autocomplete.