Sohoxic/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_sft_5k-cw-12K

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 20, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

Sohoxic/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_sft_5k-cw-12K is a 7.6 billion parameter model fine-tuned from Snowflake's Arctic-Text2SQL-R1-7B. It specializes in Text-to-SQL generation, specifically for SQL++ queries, by leveraging the NL2SQL++ v8 dataset with code-with-thought reasoning. This model is optimized for accurately translating natural language questions into complex SQL++ queries, making it highly effective for database interaction tasks.

Loading preview...

Model Overview

This model, Sohoxic/snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_sft_5k-cw-12K, is a fine-tuned version of the 7.6 billion parameter Snowflake/Arctic-Text2SQL-R1-7B base model. Its primary function is Text-to-SQL generation, specifically designed to produce SQL++ queries from natural language inputs.

Key Capabilities

  • SQL++ Query Generation: Translates natural language questions into valid SQL++ queries, adhering to specific SQL++ syntax rules and best practices.
  • Code-with-Thought Reasoning: Incorporates a detailed reasoning process, as demonstrated in the training examples, to construct complex queries step-by-step.
  • Fine-tuned for NL2SQL++ v8: Optimized using the NL2SQL++ v8 dataset, which includes examples with intricate schema understanding and query construction.
  • LoRA Fine-tuning: Utilizes Low-Rank Adaptation (LoRA) with Unsloth for efficient fine-tuning, resulting in 16-bit merged weights.

Ideal Use Cases

  • Database Interaction: Automating the generation of SQL++ queries for Couchbase or similar NoSQL databases that support SQL++.
  • Data Analysis: Empowering users to query complex datasets using natural language without needing deep SQL++ expertise.
  • Application Development: Integrating natural language interfaces into applications that require dynamic SQL++ query construction.