Craig Sanders

@AxlCruzTKH, I rebased this and tried running the tests, and ran into some issues in test_server.py. Do you want to look into this?

I'm also trying to do multiclass classification, and I stumbled upon this example. I was able to train the second model using `SoftmaxLikelihood` by making the suggested change to targets,...

I encountered this issue while trying to do beta regression. I was extremely confused why `likelihood(model(train_x)).sample(sample_shape=torch.Size([N])).shape == [N, 10, len(x)]` and not just `[N, len(x)]`. How are you supposed to...

Unless I'm misunderstanding something, the samples don't just go away. Using the example above, if I call `samples = y.sample(torch.Size([100]))`, I would expect to get a `[100, 50]` tensor back,...