jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-v5.7.5-cw-32K-16bit

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-v5.7.5-cw-32K-16bit is a 7.6 billion parameter Qwen2 model, finetuned from Snowflake/Arctic-Text2SQL-R1-7B, with a 32K context length. Developed by jastorj, this model is specifically optimized for text-to-SQL tasks. It was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds.

Loading preview...

Model Overview

This model, developed by jastorj, is a finetuned version of the Snowflake/Arctic-Text2SQL-R1-7B model. It is based on the Qwen2 architecture and features 7.6 billion parameters with a 32K context window.

Key Capabilities

  • Specialized for Text-to-SQL: The model is specifically designed and optimized for converting natural language queries into SQL commands.
  • Efficient Training: It was finetuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.

Good For

  • Database Interaction: Ideal for applications requiring natural language interfaces to databases, allowing users to query data without writing SQL manually.
  • SQL Generation: Suitable for developers and data professionals who need to automate or assist in generating accurate SQL queries from text prompts.