Qian

Sorry for the really late response. It costs me several months to merge the codebase from different collaborators on different datasets - so it's so late to release. Feel free...

@amartinson193 Thanks for the wonderful suggestion! It works well!

Maybe someone can help merge the PR? Thanks a lot! cc @vzhong

Hi Tao, I encounter a error caused by the SQL evaluation script. When there is **any column whose name contains brackets** in the predicted SQL, the evaluation script raises exception....

@binaryninja For the default fine-tuning script, I think the memory required should be around `26G` memory which exceeds the 24GB in your configuration. If you would like to fine-tune it...

Thanks for the reporting. @zhongwanjun may answer the question

@Soul-Immortal Sorry for the late response since I do not receive any notification after leaving the org Microsoft. I will try to find the code which couples ETA to other...

Maybe you can try to convert your dataset into the format of Spider as the first step? Then you may directly use UniSAR on these datasets! Ping @DreamerDeo for further...

@longxudou Maybe longxu can help on this question.

@tom68-ll Thanks for your question for our paper! Sorry we do not keep the testing code. We just employ the official code from different datasets to evaluate POET. You may...