Papers › DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL

DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL

24 Sep 2024arXiv:2409.15985archive 2025-07-28

Lixia Wu, Peng Li, Junhong Lou, Lei Fu

In addressing the pivotal role of translating natural language queries into SQL commands, we propose a suite of compact, fine-tuned models and self-refine mechanisms to democratize data access and analysis for non-expert users, mitigating risks associated with closed-source Large Language Models. Specifically, we constructed a dataset of over 20K sample for Text-to-SQL as well as the preference dateset, to improve the efficiency in the domain of SQL generation. To further ensure code validity, a code corrector was integrated into the model. Our system, DataGpt-sql, achieved 87.2\% accuracy on the spider-dev, respectively, showcasing the effectiveness of our solution in text-to-SQL conversion tasks. Our code, data, and models are available at \url{https://github.com/CainiaoTechAi/datagpt-sql-7b}

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingNatural Language QueriesText to SQLText-To-SQL

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-SQL spider datagpt-sql-7B + InvalidSQL-Feedback Exact Match Accuracy (Dev) 81.6 #15 of 20 Archive leaderboard report
Text-To-SQL spider datagpt-sql-7B + InvalidSQL-Feedback Execution Accuracy (Dev) 87.2 #15 of 20 Archive leaderboard report
Text-To-SQL spider datagpt-sql-7B Exact Match Accuracy (Dev) 80.3 #16 of 20 Archive leaderboard report
Text-To-SQL spider datagpt-sql-7B Execution Accuracy (Dev) 84.8 #16 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections