Anirudh Dagar

@KuanHaoHuang don't worry about the preview atm, I'll review the PR. Meanwhile if you are interested you can start working on the next sections for recsys chapter.

Closing this since it was fixed with the latest version of all the frameworks.

I'll try to see what can be done here in d2lbook when I work on the new infra soon.

Thanks for your work! paddlepaddle is now available in d2l-zh. 🥳 Closing this now.

I don't see any issues with any framework here since the last 2 releases. Closing this!

Have you looked at the refactored implementation? We do add space chars to tokens too. I'm closing this as resolved, if you feel something is missing, feel free to re-open!

Closing this, refactored implementation has a `training` arg in the call method. @gopalakrishna-r you can look at the latest release `http://preview.d2l.ai/d2l-en/master` for the latest changes made on master branch. Usually...

@anandrajadarsh no, Ch16 has not been implemented in PyTorch yet.

Sure, let's keep this open and we can work on the other non-urgent improvements.