Create README.md

### Performance on the BIRD Development Set

We further evaluate **DatA-SQL-3B** on the **BIRD** development set using different self-consistency voting sizes.
Under **Vote@8**, our model attains an **execution accuracy (EX) of 61.05 %**.
When the voting size increases to **Vote@32**, the EX further improves to **62.58 %**.
Overall, **DatA-SQL** achieves competitive or superior accuracy compared with GPT-based pipelines at only a fraction of their computational expense.

README.md

@@ -0,0 +1,8 @@
+---
+license: bigscience-openrail-m
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-3B-Instruc
+pipeline_tag: translation
+---