Snowflake/Qwen-2.5-coder-Arctic-ExCoT-32B

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Mar 25, 2025License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Cold

Snowflake/Qwen-2.5-coder-Arctic-ExCoT-32B is a 32.8 billion parameter Text2SQL model developed by Snowflake, based on the Qwen-2.5-coder architecture. It utilizes the ExCoT (Execution-Guided Chain-of-Thought) framework, which optimizes reasoning for Text-to-SQL tasks using SQL execution-based DPO feedback. This model excels at converting natural language queries into SQL, achieving strong performance on benchmarks like BIRD-test by leveraging execution results for optimization rather than human annotations. It is particularly suited for complex database querying applications where high accuracy in SQL generation is critical.

Loading preview...

Snowflake/Qwen-2.5-coder-Arctic-ExCoT-32B: Execution-Guided Text2SQL

Snowflake/Qwen-2.5-coder-Arctic-ExCoT-32B is a 32.8 billion parameter model developed by Snowflake, specifically designed for Text-to-SQL tasks. It is built upon the Qwen-2.5-coder architecture and incorporates the novel ExCoT (Execution-Guided Chain-of-Thought) framework. This framework distinguishes itself by optimizing the model through SQL execution-based DPO, using the actual execution results of generated SQL queries as a feedback signal, rather than relying on expensive human annotations.

Key Capabilities & Performance

  • Execution-Guided Optimization: Leverages SQL execution outcomes for direct feedback, enabling scalable and high-quality model optimization.
  • State-of-the-Art Text2SQL: Achieved strong results on the BIRD-test benchmark, demonstrating significant improvements in execution accuracy compared to base models and outperforming many general-purpose frontier models.
  • Public Dataset Training: Optimized using only public datasets like BIRD and Spider, without requiring additional Text2SQL data.
  • High Accuracy: On the BIRD-dev set, this model achieved 68.25% execution accuracy, showcasing its proficiency in complex SQL generation.

Ideal Use Cases

  • Complex Database Interaction: Excellent for applications requiring precise conversion of natural language questions into SQL queries for intricate databases.
  • Automated Data Analysis: Suitable for tools that automate data retrieval and analysis by generating accurate SQL from user prompts.
  • Benchmarking Text2SQL Solutions: Provides a strong baseline and competitive performance for evaluating Text2SQL systems.

Finetunes
1 models