🚀 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

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

1. Suggest a new feature by leaving a comment.
2. Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
3. Tell us that

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

more details at: allenai/allennlp#2264 (comment)

Spawned off https://github.com/onnx/onnx/pull/2772/files/7ab93cc1b635eada330dae7424d4ff7e8c22c295#r440422245, opening issue to track resolution

🚀 Feature

Create the metric MulticlassAUROC to allow for the AUROC metric to be used in multi-class problem settings. Or,
Expand the AUROC metric to support multi-class data, which would also directly solve this AUROC bug that instead gives a random value when used in multi-class problems: https://github.com/PyTorchLightning/

What would you like to be added: As title

Why is this needed: All pruning schedule except AGPPruner only support level, L1, L2. While there are FPGM, APoZ, MeanActivation and Taylor, it would be much better if we can choose any pruner with any pruning schedule.

**Without this feature, how does current nni

To begin I tried logging in with GitHub and also creating an account on the pyro forums, but neither of those is working.

Problem

I need to fit a batch of four independent Gaussian Processes and I don't want to have to use for loops for fitting each one. The current GP's are able to broadcast properly to my outputs, but I can't batch them so that the inputs are independent.

My input d