Numbersstation
Models by this creator
🏅
nsql-llama-2-7B
76
nsql-llama-2-7B is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks. It is based on Meta's original Llama-2 7B model and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs. The model was developed by NumbersStation. Similar models include Natural-SQL-7B by ChatDB, which also focuses on strong performance in text-to-SQL instructions, and the Llama-2 family of models developed by Meta. Model inputs and outputs Inputs Natural language prompts**: The model takes natural language prompts as input, typically in the format of text-to-SQL requests. Database schema**: The model also requires the database schema, which is provided as part of the input. Outputs SQL queries**: The model outputs SQL queries that answer the provided natural language prompts, based on the given database schema. Capabilities nsql-llama-2-7B is designed to excel at text-to-SQL generation tasks. It has been trained on a large dataset of SQL queries and text-to-SQL pairs, giving it strong performance in understanding natural language prompts and translating them into accurate SQL queries. What can I use it for? You can use nsql-llama-2-7B for a variety of applications that involve generating SQL queries from natural language inputs, such as: Intelligent database interfaces**: Build applications that allow users to interact with databases using natural language, without requiring them to write SQL directly. Automated report generation**: Generate SQL queries to extract and summarize data from databases based on user requests. SQL code completion**: Use the model to suggest or autocomplete SQL statements as users are typing. Things to try One interesting aspect of nsql-llama-2-7B is its ability to handle complex, compound questions that other models may struggle with. Try providing the model with multi-part queries or prompts that require reasoning across multiple tables or database concepts, and see how it performs. You can also experiment with fine-tuning the model on your own dataset of text-to-SQL pairs to further customize its performance for your specific use case.
Updated 5/28/2024
✅
nsql-6B
50
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks. The NSQL-6B checkpoint included in this repository is based on CodeGen-Multi 6B from Salesforce and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs. Similar models in this family include the nsql-llama-2-7B and DuckDB-NSQL-7B-v0.1 which are based on Meta's Llama-2 and fine-tuned for SQL generation, as well as the more broadly capable natural-sql-7b model from ChatDB. Model inputs and outputs NSQL-6B is a text-to-text model designed for SQL generation tasks. Given a natural language prompt and database schema, the model can generate valid SQL queries to answer the given question. Inputs Natural language prompts or questions related to a database schema Database schema definition in the form of SQL CREATE TABLE statements Outputs SQL queries that answer the given prompt or question, typically in the form of SELECT statements Capabilities The NSQL-6B model excels at translating natural language questions into SQL queries for a given database schema. It can handle a wide range of SQL constructs, including SELECT, WHERE, JOIN, ORDER BY, GROUP BY, and more. The model has shown strong performance on text-to-SQL benchmarks like Spider and GeoQuery. What can I use it for? NSQL-6B can be a powerful tool for automating the process of converting natural language requests into SQL queries. This can be useful in a variety of applications, such as: Building conversational interfaces for databases, allowing users to query data using natural language Generating SQL code to power business intelligence and reporting tools Assisting developers in quickly prototyping and iterating on database-backed applications Enhancing productivity for data analysts and scientists who need to frequently interact with databases Things to try One interesting aspect of the NSQL model family is the ability to fine-tune the models for specific database systems and use cases. For example, the DuckDB-NSQL-7B-v0.1 model is fine-tuned on DuckDB-specific text-to-SQL pairs, allowing it to generate queries that leverage DuckDB's unique features and extensions. Developers and data professionals could experiment with fine-tuning the NSQL-6B model on their own dataset of SQL queries and database schemas to create a highly customized SQL generation assistant tailored to their specific needs.
Updated 7/16/2024