sqlcoder-7b Open Source Large Model - Free Deployment, Transform Natural Language into Precise SQL Queries Instantly

Sqlcoder 7b

Developed by defog

SQLCoder-7B is a large language model specifically designed for converting natural language questions into SQL queries, fine-tuned based on Mistral-7B, with performance surpassing GPT-3.5-turbo.

Large Language Model

Transformers

Supports Multiple Languages#Natural Language to SQL #Surpasses GPT-3.5 #Database Query Optimization

Downloads 1,271

Release Time : 10/3/2023

Model Overview

SQLCoder-7B is a 7-billion-parameter model focused on natural language to SQL conversion tasks, capable of outperforming GPT-4 after fine-tuning on specific database schemas.

Model Features

High-Performance SQL Generation

Outperforms GPT-3.5-turbo and approaches GPT-4 levels under the sql-eval evaluation framework

Domain-Specific Optimization

Specially optimized and trained for natural language to SQL tasks

Open Source License

Adopts CC BY-SA 4.0 license, allowing commercial use and modifications

Model Capabilities

Natural Language to SQL

Complex Query Generation

Multi-table Join Queries

Grouping and Aggregation Queries

Date-related Queries

Use Cases

Database Queries

Business Intelligence Analysis

Automatically converts business personnel's natural language questions into SQL queries

Enhances data access capabilities for non-technical users

Data Report Generation

Automatically generates complex SQL report queries based on descriptive requirements

Reduces manual SQL writing workload

🚀 Defog SQLCoder

Defog's SQLCoder is a state - of - the - art large language model (LLM) designed to convert natural language questions into SQL queries, offering high - performance solutions for data analysis and query generation.

Interactive Demo | 🤗 HF Repo | ♾️ Colab | 🐦 Twitter

🚀 Quick Start

Using SQLCoder

You can use SQLCoder via the transformers library by downloading our model weights from the Hugging Face repo. We have added sample code for inference on a sample database schema.

python inference.py -q "Question about the sample database goes here"

# Sample question:
# Do we get more revenue from customers in New York compared to customers in San Francisco? Give me the total revenue for each city, and the difference between the two.

You can also use a demo on our website here, or run SQLCoder in Colab here

Hardware Requirements

SQLCoder has been tested on an A100 40GB GPU with bfloat16 weights. You can also load an 8 - bit and 4 - bit quantized version of the model on consumer GPUs with 20GB or more of memory – like RTX 4090, RTX 3090, and Apple M2 Pro, M2 Max, or M2 Ultra Chips with 20GB or more of memory.

✨ Features

Key Features

SQLCoder-7B is a 7B parameter model that outperforms gpt - 3.5 - turbo for natural language to SQL generation tasks on our [sql - eval](https://github.com/defog - ai/sql - eval) framework, and significantly outperforms all popular open - source models. When fine - tuned on a given schema, it also outperforms gpt - 4.
SQLCoder was trained on more than 20,000 human - curated questions based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.

📊 Results

Results on novel datasets not seen in training

Property	Details
Model Type	SQLCoder-7B, defog-sqlcoder2, gpt4, gpt - 3.5, claude - 2, claude_instant_1, text - davinci - 003
Performance (perc_correct)
	gpt4-2023 - 10 - 04: 82.0
	defog - sqlcoder2: 74.5
	gpt4-2023 - 08 - 28: 74.0
	defog - sqlcoder - 7b: 71.0
	gpt - 3.5-2023 - 10 - 04: 66.0
	claude - 2: 64.5
	gpt - 3.5-2023 - 08 - 28: 61.0
	claude_instant_1: 61.0
	text - davinci - 003: 52.5

Results by question category

query_category	gpt - 4	sqlcoder2 - 15b	sqlcoder - 7b	gpt - 3.5	claude - 2	claude - instant	gpt - 3
date	72	76	64	68	52	48	32
group_by	91.4	80	82.9	77.1	71.4	71.4	71.4
order_by	82.9	77.1	74.3	68.6	74.3	74.3	68.6
ratio	80	60	54.3	37.1	57.1	45.7	25.7
join	82.9	77.1	74.3	71.4	65.7	62.9	57.1
where	80	77.1	74.3	74.3	62.9	60	54.3

📄 License

The code in this repo (what little there is of it) is Apache - 2 licensed. The model weights have a CC BY - SA 4.0 license. The TL;DR is that 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.

📋 Todo

[x] Open - source the v1 model weights
[x] Train the model on more data, with higher data variance
[ ] Tune the model further with Reward Modelling and RLHF
[ ] Pretrain a model from scratch that specializes in SQL analysis

⚠️ Important Note

This model is now outdated. Please use [defog/sqlcoder - 7b - 2](https://huggingface.co/defog/sqlcoder - 7b - 2) for much better performance!

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご