Fix tokenizer typos, add newlines

Fix some issues in the tokenizer.

Mainly, fix a problem where newlines weren't present in the tokenizer model. This meant any whitespace was silently deleted and newlines weren't a thing. This could introduce issues for datasets such as wikitext103, where newlines delimited titles and actual text.

Re-train the wikitext tokenizers with newlines.

requested review from @vlad_andrei.badoiu1

assigned to @agherghescu2411

merged

mentioned in commit f3c62726