Yida

**Description:** Added dataloader for [Chinese-gpt](https://github.com/lemon234071/Chinese-gpt.git) implemented by [pytorch-transformers](https://github.com/huggingface/transformers.git). **Reference Issues:** #XX (XX is the issue number you work on) Dataloader for huggingface transformers #1300 1, Added two classes -- HGFSingleTurnDialog,...

URLs are not matched

1

text = "郭麒麟打卡,且听他分享防疫小知识https://www.zhihu.com/qution/319823639哈哈http//t.cn/a67ov8bt哈哈哈http://t.c" cleantext.replace_urls(text, "XXX") output: 郭麒麟打卡,且听他分享防疫小知识https://www.zhihu.com/qution/319823639哈哈http//t.cn/a67ov8bt哈哈哈哈http://t.c Expected: 郭麒麟打卡,且听他分享防疫小知识XXX哈哈XXX哈哈哈哈XXX

Could you specify the installation environment？such as pytorch and cuda version. There too much error when installing and runing. Thank you so much. RuntimeError: !dets.type().is_cuda() INTERNAL ASSERT FAILED at movienet/tool

How to reproduce the same training process when using "train_from"

4

Dear, When the model training was forced to stop due to an accident. I use the opt "train_from" to continue training from the checkpoint. But the result is different from...

var =std**2 ?

How to train with Twitter data?

1

Thank you for your interest work . May i know how to use the Twitter id to train on the Twitter data? Thank you again

Can you provide an example of text like Sentiment classification?

2

Specifically, how to deal with word embedding....