How to use the model?
How can I use this model for text2sql on my own data?
Prepare your data in the same format as SPIDER. And perform your task following https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/graphix. Thanks.
Hi, is the relational graph required to be a part of the training input as well? Thanks.
@zea
Yep, the graph_pedia_total.bin store the heterogeneous graph among question, schema tokens. Our code already process it in a portable end-to-end way.
Is it possible to perform fine-tuning on my data using a consumer computer without a dedicated GPU?
Hi, I was trying to read your "graph_pedia_total.bin" but got the following error. Could you kindly advise me on this please? Thanks.
This is the error.
"Can't get attribute 'DGLHeteroGraph' on <module 'dgl.heterograph' from '/usr/local/lib/python3.10/dist-packages/dgl/heterograph.py'>"
Hi can u pls provide an example of how we can use the model, at the moment it gives an error of I cant call generate on the model!
我看了那个repo，有点复杂，有没有简单可运行的方法
Hi @patrickNLP ,
If you write a simple blog or README.md file for how to use this model with the code explanation for beginners, that would be really beneficial for us.
and also I can wait to see your upcoming works in this field.
Thnks buddy