xiyan

Thanks for your excellent work. I have noticed that the best results will be obtained after 230k training steps. I am curious what the ROUGE is after 100k training steps?thx

Error about 'Matrix already exists' under decode mode.

6

Thanks for your impressive work. In fact, I am trying to modify something about this structure, while I did not modify anything about attention mechanism. After I train my new...

Dataset

19

Thanks for your excellent works. Would you mind provide XSum dataset directly just like CNN/Dialy Mail that we are familiar with? I believe it may save time and be more...

difference between logits and topic_addition

3

Thanks for your excellent work~ Actually, I rebuild this structure by tensorflow while I met some problem. I discover that logits and topic_addition may own different scale, such as logits...

calculation of kl_divergence

2

Hi, thanks for your excellent work. I have some question about formula of kl_divergence. As mentioned in the code, the formula is : kl_divergence = torch.ones_like(mu) + 2 * log_sigma...

I met some problem on installing DB_File module. When I try to use 'ppm install DB_File', it showed that 'no missing package to install', but when I verify by ppm,...