FineTune LLM for regex


I’ve been trying to find research on this and also been searching the models and this forum but can’t seem to find an example of where someone has used an LLM specifically to write regular expressions.

I’m looking to pass system/app logs as input to the model and have it return back a regular expression to parse out fields.

I have a somewhat large dataset of examples to fine tune the model with to see if it’s any good.

What I’m struggling with is identifying which LLM would be good to start with and am looking to see if anyone has some ideas on that.

Thanks!! :slight_smile:

Hey, Have you identified any model to start with for this problem? @Tyler1010