# Database Query Generation

A text-to-SQL generation language model specifically designed for Postgres, Redshift, and Snowflake databases, with performance comparable to cutting-edge general-purpose models.

This is a fine-tuned model based on TinyLlama-1.1B-Chat-v1.0, specifically designed to convert natural language questions and table structure definitions (DDL) into SQL queries.

A text-to-SQL model distilled from Llama 1B, outperforming ChatGPT and Claude in multiple benchmarks

SQLCoder-34B is a 34-billion-parameter natural language to SQL query model launched by Defog, outperforming mainstream models like GPT-4 in the sql-eval benchmark

A lightweight model fine-tuned on T5-small that generates SQL queries from natural language with table structures, supporting multi-table join operations.

CodeS-7B is a large language model optimized for SQL generation, based on incremental pre-training of StarCoderBase-7B, supporting a maximum context length of 8,192 tokens.

This is a Flan-T5 based text-to-SQL conversion model that supports generating SQL queries from natural language questions and table schemas.

A fine-tuned text-to-SQL conversion model based on T5-3B architecture, significantly improving structured query generation accuracy through PICARD constrained decoding

This is a fine-tuned version of Google's T5-small model on the WikiSQL dataset, designed to convert English natural language queries into SQL statements.