Qian

@liu-nlper Thanks for your quick response! I will try again following your kind suggestions. If it is solved, I will get back to report the experimental results.

After struggling for a few days, finally I have to admit that it is difficult to incorporate the official 12-layer BERT chinese version into the task of rewrite (either for...

@Akshaysharma29 You could try our [codebase](https://github.com/microsoft/ContextualSP/tree/master/semantic_parsing_in_context#predict-on-custom-data) which supports predicting SQL for dialogues on your custom data.

@srewai Hi! Thanks for the very interesting question (Yes it is quite challenging). I think the best practise may be using the text-to-SQL parser instead of current text-to-answer models on...

@srewai Not yet maybe because it is for WikiSQL haha. But I think it is worthy to have a try on that! Also, I think dense retrieval may be one...

Closed since no more activity. Feel free to re-open it :)

Closed since there is no more activity.

Closed since there is no more activity.

@authurlord I'm not the author of this repo and accidently see the repo. For LoRA weights merging, lorahub is a candidate method (https://github.com/sail-sg/lorahub).

Sorry the first author cannot recover the `HumanSimulator` class since the original codebase is cleared after his internship 😓 You may have to implement one by yourself. So sorry for...