I think you nailed it.
For us it’s classifiers that we train for very specific domains.
You’d think it’d be better to just finetune a smaller non-LLM model, but empirically we find the LLM finetunes (like 7B) perform better.
For us it’s classifiers that we train for very specific domains.
You’d think it’d be better to just finetune a smaller non-LLM model, but empirically we find the LLM finetunes (like 7B) perform better.