NguyenCX/Qwen2.5_coder_7B_instruct_GRPO_BIRD

QWEN2.5CODER-7B-INSTRUCT SFT+GRPO

This model was fine-tuned with cold-start SFT and Reinforcement learning with GRPO The BIRD training data was used for reinforcement learning

Original model

• License: Apache-2.0

Intended use

Text-to-SQL inference experiments with vLLM.

Attribution