Sharing training scripts
Hi,
Thanks for sharing the model!
Do you think it'll be possible to share the training scripts?
Thank you!
Of course, would you like me to add it to the repo here, or send it to you directly by email or something?
Cheers
Adding them to the repo would work great!
Thanks!
Hello, did you end up sharing the training scripts somewhere? If not, would it be possible to do that? Thanks in advance =)
Hey, I am working on implementing the same method as you guys for a low resource language. How did you guys implement the pre-training objective described in the paper? I am unable to find the probabilities they used for these operations:
a) drop spans of tokens b) swap tokens c) drop spans of characters d) swap characters e) insert characters3 f) lower-case a word g) upper-case the first letter.
Hearing from you would be a huge help!
Thanks! :)