juierror

/

flan-t5-text2sql-with-schema-v2

like 30

@moon-cake22 Thank you very much for the testing.

I notice this point as well. The current result is not good for some type of table. I will try to improve it further.

@juierror . Could you please provide scripts for how you're finetuning this model? Thanks!

@temiwale88

Sorry for late reply, here is the code

https://github.com/juierror/flan-t5-text-to-sql/blob/main/flan_t5_text2sql_multi_table.ipynb

Thank you!

Thanks for letting us play around with the model. Here is another prompt that came out wrong, if you want more training material:

print(inference(
"Among the artists having concerts in year 2020, which artist has a song whose title equals the name of the stadium on which the concert takes place?",
{
"stadium": ["stadium_id", "location", "name", "capacity", "highest", "lowest", "average"],
"singer": ["singer_id", "name", "country", "song_name"],
"concert": ["concert_id", "stadium_id", "year"],
"singer_in_concert": ["concert_id", "singer_id"]
}))

Returned (which would not work):

SELECT T1.song_name
FROM singer AS T1
JOIN concert AS T2 ON T1.singer_id = T2.singer_id
WHERE T2.year = 2020
AND T1.stadium_id = (
SELECT stadium_id FROM concert WHERE YEAR = 2020
)

@tordbb Thank you very much.

@juierror Have you retrained the model to reduce the error queries as mentioned by other users? Where can I find the new model?

@Kushrjain

To be frank, I still did not have a time to retrain the model. The current model is still not updated.