Open riktimmondal opened 5 years ago
I have a similar question. My understanding is that the output should be a distribution over tokens for each predicted (i.e., "next") output, but I'm wondering how to get an actual string result?... Did you manage to get your next sentence generation working?
I am using for next sent. gen so while it has stored model in .ep* format but how to run my test dataset using those models.
Thanks