Re:Show HN: Natural-SQL-7B, a strong text-to-SQL model
by thecalebf on Monday February 05, 2024 @10:47AM
(#39262351)
No, those are benchmark, evaluation questions. The fine tune dataset was a custom, synthetically generated dataset of ~20k PostgreSQL Text to SQL pairs covering different SQL categories and question types.
I mention a little more about it here https://x.com/calebfahlgren/status/1754247740291207198?s=20
https://github.com/defog-ai/sql-eval/blob/main/data/question...