add_prefix_space missing from tokenization

In your docs, you mention that whenever the GPT2 tokenizer is used, there should be a space prefixed to the input string: https://huggingface.co/transformers/main_classes/tokenizer.html#transformers.PreTrainedTokenizer

However, in the `get_dataset()` function in `utils.py`, you do not add `add_prefix_space=True` to the tokenizer call. Why is this the case?

Thanks for this great toolkit!

Start with get_dataset() in utils.py and compare its tokenizer call with the GPT2 guidance in the linked documentation. Determine whether the missing add_prefix_space=True is intentional; done means either updating the call or documenting why it should remain unchanged.

Written by the indexing model from the issue text.