Miguel-Angel Monjas

We are open-sourcing SQLCoder, state of the art model for converting natural language questions to SQL queries! github.com/defog-ai/sqlcoder SQLCoder outperforms OpenAI’s gpt-3.5-turbo, and significantly outperforms all major open-source models for generic SQL schemas in Postgres. When fine-tuned on an individual DB schema, it outperforms gpt-4. The model is small enough to run on a single A100 40GB in 16 bit floats, or on a single high-end consumer GPU (like RTX 3090/4090) with 8bit quantization. We are also open-sourcing our framework for evaluating LLM generated SQL. SQL can be tricky to evaluate (see here for why: nitter.gq/rishdotblog/stat…). With rigorous, open and reproducible testing, we hope to advance the frontier of OSS text-to-SQL solutions. The model weights have a CC BY-SA 4.0 license. You can use and modify the model for any purpose – including commercial use. However, if you modify the weights (for example, by fine-tuning), you must open-source your modified weights under the same license terms. SQLCoder has been deployed inside Healthcare and Finance enterprises – where data privacy is critical – and has worked remarkably well. We will share more about the model in the coming days!