DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL
This work aims to democratize data access and analysis for non-expert users by providing an open-source alternative to closed-source large language models, though it appears incremental in its approach.
The paper tackles the problem of translating natural language queries into SQL commands by proposing a suite of compact, fine-tuned models with self-refine mechanisms, achieving 87.2% accuracy on the spider-dev benchmark.
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}