What is the tgt in the torch.nn.Transformer?

Specifically, I see here in the docs:

>>> transformer_model = nn.Transformer(nhead=16, num_encoder_layers=12)
>>> src = torch.rand((10, 32, 512))
>>> tgt = torch.rand((20, 32, 512))
>>> out = transformer_model(src, tgt)

I’m unsure what the tgt is. The docs say tgt – the sequence to the decoder (required).. But I’m not passing a sequence to the decoder. I want the decoder to give me an output, don’t I?