FINER-SQL-4B-BIRD / README.md
thanhdathoang's picture
Update README.md
fc381fa verified
metadata
base_model:
  - griffith-bigdata/Qwen3-4B-SQL-Writer

FINER-SQL-4B-BIRD

Trained from griffith-bigdata/Qwen3-4B-SQL-Writer using GRPO with two additional dense rewards from the FINER-SQL paper:

๐Ÿง  Memory Reward โ€” aligns reasoning with verified traces
โš™๏ธ Atomic Reward โ€” measures operation-level SQL overlap

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

๐Ÿ“„ See other models: https://huggingface.co/collections/griffith-bigdata/finer-sql

๐Ÿ“„ Github code: https://github.com/thanhdath/finer-sql/tree/main