Hi, I am interested in using the DeBERTa model that was recently implemented here and incorporating it into FARM so that it can also be used in open-domain QA settings through Haystack.

Just wondering why there's only a Slow Tokenizer implemented for DeBERTa and wondering if there are plans to create the Fast Tokeni

Change tensor.data to tensor.detach() due to
pytorch/pytorch#6990 (comment)
tensor.detach() is more robust than tensor.data.

A user reported a documentation issue on the mailing list: https://groups.google.com/g/gensim/c/8nobtm9tu-g.

The report shows two problems:

1. Something changed with wmdistance between 3.8 and 4.0 that is not properly captured in the Migration notes.

2. The [WMD tutorial](https://radimrehurek.com/gensim_4

While setting train_parameters to False very often we also may consider disabling dropout/batchnorm, in other words, to run the pretrained model in eval mode.
We've done a little modification to PretrainedTransformerEmbedder that allows providing whether the token embedder should be forced to eval mode during the training phase.

Do you this feature might be handy? Should I open a PR?

Current pytorch implementation ignores the argument split_f in the function train_batch_ch13 as shown below.

def train_batch_ch13(net, X, y, loss, trainer, devices):
    if isinstance(X, list):
        # Required for BERT Fine-tuning (to be covered later)
        X = [x.to(devices[0]) for x in X]
    else:
        X = X.to(devices[0])
...

Todo: Define the argument `

Hello spoooopyyy hackers 🎃

This is a Hacktoberfest only issue! 👻

This is also data-sciency!

The Problem

Our English dictionary contains words that aren't English, and does not contain common English words.

Examples of non-common words in the dictionary:

"hlithskjalf",
  "hlorrithi",
  "hlqn",
  "hm",
  "hny",
  "ho",
  "hoactzin",
  "hoactzine