Downloads · 30 days
2.5K
2% of all-time downloads
Arctic-Text2SQL-R1-7B
Snowflake/Arctic-Text2SQL-R1-7B
Arctic-Text2SQL-R1-7B is a machine learning model from Snowflake. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Arctic-Text2SQL-R1-7B is a 7-billion-parameter Text-to-SQL model fine-tuned using Group Relative Policy Optimization (GRPO) with a simple execution-based reward signal. It converts natural language questions into exec…
All-time downloads
102K
Public
Parameters
7.6B
15.2 GB on disk
Likes
79
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- May 22, 2025
- Updated
- May 29, 2025
- SHA
- 2d73faca
Base models
Model card
From the Hugging Face model README
Overview
Arctic-Text2SQL-R1-7B is a 7-billion-parameter Text-to-SQL model fine-tuned using Group Relative Policy Optimization (GRPO) with a simple execution-based reward signal. It converts natural language questions into executable SQL queries.
Read more in our paper: Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL.
Key Features
- Lightweight RL formulation: Uses only execution correctness and syntax validity as rewards.
- State-of-the-art performance: Achieves 68.9% execution accuracy on BIRD-dev and 68.5% on BIRD-test, with an average of 57.2% across six benchmarks (BIRD, Spider, Spider2.0, Spider-DK, EHRSQL, ScienceBenchmark)
- Efficiency: Outperforms many 70B+ models with only 7B parameters.
Intended Use
This model is designed for:
- Interactive natural language interfaces to relational databases.
- Data analytics tools enabling non-technical users to query databases.
Not intended for:
- Generation of non-SQL text or free-form natural language tasks.
- Production systems without validation, especially in safety-critical domains.
| Benchmark | Dev/Test Accuracy |
|---|---|
| BIRD-dev | 68.9% |
| BIRD-test | 68.5% |
| Spider-test | 88.8% |
| Spider2.0-DK | 15.6% |
| EHRSQL | 36.7% |
| ScienceBenchmark | 51.8% |
| Average | 57.2% |
Ethical Considerations
- Avoid using for private or sensitive data without proper oversight.
- Validate generated SQL to prevent data leakage or unauthorized access.
- Type
- qwen2
- License
- apache-2.0
- Created
- May 22, 2025
- Updated
- May 29, 2025