jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 21, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K model is a 7.6 billion parameter language model developed by Snowflake, fine-tuned for Text-to-SQL generation. It is based on the Arctic-Text2SQL-R1-7B architecture and specifically optimized for generating SQL++ queries from natural language. This model excels at complex SQL query generation, incorporating code-with-thought reasoning and error analysis for improved accuracy and robustness, particularly for Couchbase SQL++.

Loading preview...

Overview

This model, jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K, is a specialized 7.6 billion parameter variant of Snowflake's Arctic-Text2SQL-R1-7B. It has been fine-tuned using Low-Rank Adaptation (LoRA) with Unsloth on the NL2SQL++ v8 dataset, which includes code-with-thought reasoning. The model's primary function is to accurately translate natural language queries into valid SQL++ queries, specifically designed for Couchbase environments.

Key Capabilities

  • Advanced Text-to-SQL Generation: Converts complex natural language requests into precise SQL++ queries.
  • Error Analysis and Correction: Demonstrates the ability to analyze SQL++ errors and propose corrected queries, enhancing reliability in dynamic database environments.
  • Code-with-Thought Reasoning: Incorporates a reasoning process to generate more robust and contextually appropriate SQL++ queries.
  • Couchbase SQL++ Optimization: Tailored to adhere to Couchbase SQL++ syntax and best practices, including handling specific data structures and query patterns.

When to Use This Model

  • Automated SQL++ Query Generation: Ideal for applications requiring automatic generation of SQL++ queries from user input.
  • Database Interaction: Useful for developers and data analysts working with Couchbase databases who need to quickly generate or debug SQL++ queries.
  • Educational Tools: Can serve as a valuable tool for learning and understanding complex SQL++ query construction and error handling.