Which statement describes a transformer?

It's a recurrent neural network $($RNN$)$ that's made up of gated recurrent unit

$($GRU$)$ nodes.

It's a recurrent neural network $($RNN$)$ that uses long short$-$term memory

LSTM$.$

It's a recurrent neural network $($RNN$)$ with a very large gradient.

Its a sequence$-$to$-$sequence $($Seq$2$Seq$)$ model with an attention layer.