---
base_model:
- griffith-bigdata/Qwen3-4B-SQL-Writer
---

# FINER-SQL-4B-BIRD

Trained from [`griffith-bigdata/Qwen3-4B-SQL-Writer`](https://huggingface.co/griffith-bigdata/Qwen3-4B-SQL-Writer) using GRPO with two additional dense rewards from the FINER-SQL paper:

🧠 Memory Reward — aligns reasoning with verified traces  
⚙️ Atomic Reward — measures operation-level SQL overlap  

✅ 68.4% EX on BIRD when training only on BIRD train; infer on a 24 GB GPU

📄 See other models: https://huggingface.co/collections/griffith-bigdata/finer-sql

📄 Github code: https://github.com/thanhdath/finer-sql/tree/main