GitLab

Adding --do_lower_case for all uncased BERTs examples

Fixing the commentary of the `SquadExample` class.

I had missed those, it should make sense to use them

Readme file links

Correct assignement for logits in classifier example

I tried to address https://github.com/huggingface/pytorch-pretrained-BERT/issues/76
should be correct, but there's likely a more efficient way.

Point typo fix

Update finetuning example in README adding --do_lower_case

Should be consistent with the fact that an uncased model is used

Fix internal hyperlink typo

Third release

fix typo in input for masked lm loss function

Updated quick-start example with `BertForMaskedLM`

As `convert_ids_to_tokens` returns a list, the code in the README currently throws an `AssertionError`, so I propose I quick fix.

Bug fix in examples;correct t_total for distributed training;run pred…