jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5.2-cw-16K

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

This model is a fine-tuned version of Snowflake's Arctic-Text2SQL-R1-7B, specifically optimized for Text-to-SQL generation. It leverages the NL2SQL++ v8 dataset, incorporating code-with-thought reasoning to enhance its ability to convert natural language queries into SQL++ statements. Fine-tuned using LoRA with Unsloth and 16-bit quantization, this model is designed for accurate and efficient SQL query generation from complex natural language inputs.

Loading preview...

Model Overview

This model, jastorj/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5.2-cw-16K, is a specialized fine-tune of the Snowflake/Arctic-Text2SQL-R1-7B base model. Its primary function is Text-to-SQL generation, converting natural language queries into valid SQL++ statements.

Key Capabilities & Features

  • Text-to-SQL Generation: Excels at translating complex natural language into SQL++ queries.
  • Enhanced Reasoning: Fine-tuned on the NL2SQL++ v8 dataset, which includes "code-with-thought" reasoning examples, improving its ability to understand and generate logical SQL structures.
  • Efficient Fine-tuning: Utilizes LoRA (Low-Rank Adaptation) with Unsloth for efficient adaptation.
  • Quantization: Features 16-bit merged weights for optimized performance.
  • Context Length: Supports a maximum sequence length of 16,000 tokens, allowing for detailed schema and query inputs.

Ideal Use Cases

This model is particularly well-suited for applications requiring precise and context-aware SQL generation, such as:

  • Database Interaction: Building natural language interfaces for querying databases.
  • Data Analytics: Assisting users in generating complex SQL queries without deep SQL knowledge.
  • Developer Tools: Integrating into IDEs or data platforms to provide SQL query suggestions or generation from user prompts.