🚀 Feature request

modeling_longformer.py has the classes LongformerForSequenceClassification, LongformerForMultipleChoice and LongformerForTokenClassification which are not present in modeling_tf_longformer.py at the moment.
Those classes should be equally added to modeling_tf_longformer.py.

Motivation

The pretrained weights for TFLongformer are available so that these

Well, Gumbel Distribution is magical. Basically, given a sequence of K logits, i.e., "\log a_1, \log a_2, ..., \log a_K" and K independent gumbel random variables, i.e., "g_1, g_2, ..., g_K". We have

\argmax_i \log a_i + g_i ~ Categorical({a_i / sum(a)})

This gives you a very simple way to sampl