add a suggestion since code snippet has been repeated.

[Shuyib]

I noticed there's a code cell that has been repeated. I suggest maybe to rename the variable to token_ids_ind (token ids individual) maybe to show how to subset the tensor. Just for illustrative purposes. Based on the previous explanation. Thank you.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[rasbt]

Thanks for the note! I addressed it in #212 . I like your suggestion, but checking with the book, I see that I annotated it as

Token IDs:
 tensor([[[16657], # First batch
         [  339],
         [42826]],
        [[49906], # Second batch
         [29669],
         [41751]]])

which should probably help making it clear.

[Shuyib]

That works better 👍🏿 . Apologies for the commit to the main branch.