No, those are benchmark, evaluation questions. The fine tune dataset was a custo... | Hacker News

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

		thecalebf on Feb 5, 2024 \| parent \| context \| favorite \| on: Show HN: Natural-SQL-7B, a strong text-to-SQL mode... 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

Semaphor on Feb 5, 2024 [–]

So this is essentially postgres only? Or how will it handle e.g. MS SQL Schemas and output?

thecalebf on Feb 5, 2024 | [–]

Currently Postgres yes, already working on a dataset with more DDLs like MySQL, DuckDB, MSSQL, etc for a second iteration.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact