MohanaSudhan/text2sql-qwen7b-sft-bird

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 8, 2026Architecture:Transformer Featherless Exclusive Cold

MohanaSudhan/text2sql-qwen7b-sft-bird is a 7.6 billion parameter language model fine-tuned from Qwen/Qwen2.5-Coder-7B-Instruct. This model specializes in text-to-SQL tasks, leveraging its base architecture's coding capabilities. It was trained using the TRL framework to enhance its performance in generating SQL queries from natural language. Its primary application is converting natural language questions into executable SQL statements.

Loading preview...

Model Overview

MohanaSudhan/text2sql-qwen7b-sft-bird is a 7.6 billion parameter language model, fine-tuned from the robust Qwen/Qwen2.5-Coder-7B-Instruct base model. This specialization focuses on text-to-SQL conversion, making it adept at translating natural language queries into structured SQL commands.

Key Capabilities

  • Text-to-SQL Generation: Excels at interpreting natural language questions and generating corresponding SQL queries.
  • Fine-tuned Performance: Utilizes the TRL (Transformers Reinforcement Learning) framework for supervised fine-tuning (SFT), enhancing its accuracy and relevance for SQL generation tasks.
  • Coder Base: Built upon a Coder model, providing a strong foundation for understanding and generating code-like structures.

Good For

  • Database Interaction: Ideal for applications requiring natural language interfaces to databases.
  • Automated SQL Query Generation: Useful for developers and data analysts to quickly generate SQL without manual coding.
  • Educational Tools: Can serve as a component in tools designed to teach or assist with SQL query construction.