zhen

谷歌云盘下载链接错误

1

链接跳转至当前项目，麻烦作者更新一下

have you ever try a bigger corpus

1

I find `BERT` uses `BookCorpus (800M words)` and `Wikipedia (2500M words)` but `GPT` only uses `BookCorpus`, even `BERT` has complex model structure which may leads to effect representation ability, the...

questions about quora data split

1

Hi, thanks for your excellent work! Your split for quora data is used for so many succeed works, and now I want to use it. But I find the pairID...

Could you upload the code to generate handwriting formulas?

6

Hi~I want to generate some handwriting image, can you share your code?

I noticed that you commented out the code about char embedding, can you tell me the reason?

could you release your `fasttext` model or its link? and how to use fasttext in this model? thx