Ask HN: When is fine-tuning a small LLM worth it?

A Hacker News user posting as kooldeep7 asked the site's community when fine-tuning a small LLM is worth it, requesting accounts of the task, the model trained, and the results. The Ask HN thread, submitted 13 minutes before the page was captured, had drawn 4 points and no comments at that time.

| Guidelines newsguidelines.html \| FAQ newsfaq.html \| Lists lists \| API https://github.com/HackerNews/API \| Security security.html \| Legal https://www.ycombinator.com/legal/ \| Apply to YC https://www.ycombinator.com/apply/ \| Contact mailto:hn@ycombinator.com | | | Hacker News news new newest \| past front \| comments newcomments \| ask ask \| show show \| jobs jobs \| submit submit | login login?goto=item%3Fid%3D49807413 | | | | Ask HN: When is fine-tuning a small LLM worth it? item?id=49807413 | | | | 4 points by kooldeep7 user?id=kooldeep7 13 minutes ago item?id=49807413 \| hide hide?id=49807413&goto=item%3Fid%3D49807413 \| past https://hn.algolia.com/?query=Ask%20HN%3A%20When%20is%20fine-tuning%20a%20small%20LLM%20worth%20it%3F&type=story&dateRange=all&sort=byDate&storyText=false&prefix&page=0 \| favorite fave?id=49807413&auth=bd45abcdda65bf55fc398baa9fe65e92113349d0 \| discuss item?id=49807413 | | | | I'd be interested in hearing about your experiences. What kind of task did you use it for, what model did you train, and what were the results? Feel free to share examples of what you've tried. |