> have seen anecdotes where finetuning a small model on domain data makes the mo... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		koakuma-chan 10 months ago \| parent \| context \| favorite \| on: DeepSeek-Prover-V2 > have seen anecdotes where finetuning a small model on domain data makes the model lose coherence on other topics This is expected behaviour.

simianwords 10 months ago [–]

i know. so why don't we have domain specific models as tools in consumer llm products

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact