What's changed
This version, we have refactored the entire project code and made related optimizations, achieving an execution accuracy on the Spider evaluation set that surpasses GPT-4 (compared with third-party evaluation results).
1. Initial code refactoring by csunny
2. Framework for code refactoring confirmed by wangzaistone and csunny
3. Code refinement and iteration for configs, data, data_process, eval, llm_base, predict, train etc, primarily developed by wangzaistone ,with assistance from Jian1273 zhanghy-sketchzh junewgl
4. relevant training experiments and results by wangzaistone and Jian1273