Tomasz Pietruszka

`spm.model` and `spm.vocab` in the same directory - the next thing your code will complain about - are files containing a SentencePiece tokenization model, trained on a specific dataset. I...

I am beginning to implement various options of attention on top of ulmfit, so obviously I've looked at this code. I do not really understand how it is used here....

@dust0x I think all approaches are worth testing... Recently I have been experimenting with different variants of attention, applied to the LM outputs before pooling, on the imdb task. I've...

I see... I should have read the code more carefully. It does not feel like the perfect solution, but in practice, I think such an option could be useful even...

@vivekratnavel sorry to bother you but I have some problem, and not having much experience in Node-related stuff I'm not sure where the problem is. when I've just cloned omniboard,...

Thanks for the nvm tip! With your versions, I still get the error. After following your latest link it seems like it is an issue with NPM. They have an...

@jdanyow I see you've closed #221 in favor of this PR, but do you need me to add something more here? Or is it OK to merge?

Unfortunately, I do not know anything other than what's in this PR Maybe @jdanyow does not see these @ mentions? I've sent a review request.

> I don’t think discussions are going to use reversed order either. Could you please elaborate? "Either", as in something else won't use it? :thinking: The idea is to have...

@zsdycs good comments and improvements, thanks Please feel free to branch off of this and open your own pull request. (or one starting from the current master branch?) To be...