In RNN(RNNBase).forward() function, out is produced by a built-in function
result = _impl(input, batch_sizes, hx, self._flat_weights, self.bias,
self.num_layers, self.dropout, self.training, self.bidirectional)
if I want to write a pytorch RNN model from the very beginning, like I’m the pytorch author , how can I find out the source code in pytorch?