is gpt-3.5-turbo-0125 a material improvement? u think it’d make a difference over the 1106 mdoel?
“This model will also have various improvements including higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.”
I’m a little disappointed w the lack of allowing gpt4 fine tune access…
I find the current 3.5 base model fine tunes tend to struggle w generalization / RAG techniques / long context