onekq-ai/OneSQL-v0.2-Qwen-3B

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:May 13, 2025Architecture:Transformer0.0K Featherless Exclusive Cold

OneSQL-v0.2-Qwen-3B by onekq-ai is a 3.1 billion parameter full-weight model based on the Qwen architecture, specifically fine-tuned for SQL generation. It excels at translating natural language queries into SQL code, given a database schema. This model is designed to assist developers in quickly generating accurate SQL queries for various database operations.

Loading preview...

OneSQL-v0.2-Qwen-3B: SQL Generation Model

OneSQL-v0.2-Qwen-3B is a 3.1 billion parameter model developed by onekq-ai, representing the full-weight version of its predecessor, OneSQL-v0.1-Qwen-3B. This model is specialized in generating SQL queries from natural language prompts, making it a valuable tool for database interaction and development.

Key Capabilities

  • SQL Code Generation: Translates natural language questions into executable SQL queries.
  • Schema-Aware: Utilizes provided CREATE TABLE schema definitions to generate contextually relevant SQL.
  • Prompt-Driven: Designed to work with a specific prompt format, starting with schema, followed by a natural language query, and ending with SELECT to trigger completion.

How it Differs

Unlike general-purpose large language models, OneSQL-v0.2-Qwen-3B is highly optimized for a single, critical task: SQL generation. Its fine-tuning specifically targets the nuances of database schema interpretation and query construction, aiming for high accuracy and relevance in SQL output. This specialization allows it to perform effectively in scenarios requiring precise SQL code generation, distinguishing it from broader instruction-tuned models.

Should I Use This?

This model is ideal for use cases where automated SQL query generation is beneficial, such as:

  • Developer Tools: Integrating into IDEs or data analysis platforms to assist developers in writing SQL.
  • Data Exploration: Enabling users to query databases using natural language without deep SQL knowledge.
  • Educational Purposes: Helping learners understand SQL query construction based on schema and natural language intent.

Finetunes
2 models