, 3, 2, 9]])
        >>> # xdoctest: +IGNORE_WANT("non-deterministic")
        >>> embedding(input)
        tensor([[[-0.0251, -1.6902,  0.7172],
                 [-0.6431,  0.0748,  0.6969],
                 [ 1.4970,  1.3448, -0.9685],
                 [-0.3677, -2.7265, -0.1685]],

                [[ 1.4970,  1.3448, -0.9685],
                 [ 0.4362, -0.4004,  0.9400],
                 [-0.6431,  0.0748,  0.6969],
                 [ 0.9124, -2.3616,  1.1151]]])


        >>> # example with padding_idx
        >>> embedding = nn.Embedding(10, 3, padding_idx=0)
        >>> input = torch.LongTensor([[0, 2, 0, 5]])
        >>> embedding(input)
        tensor([[[ 0.0000,  0.0000,  0.0000],
                 [ 0.1535, -2.0309,  0.9315],
                 [ 0.0000,  0.0000,  0.0000],
                 [-0.1655,  0.9897,  0.0635]]])

        >>> # example of changing `pad` vector
        >>> padding_idx = 0
        >>> embedding = nn.Embedding(3, 3, padding_idx=padding_idx)
        >>> embedding.weight
        Parameter containing:
        tensor([[ 0.0000,  0.0000,  0.0000],
                [-0.7895, -0.7089, -0.0364],
                [ 0.6778,  0.5803,  0.2678]], requires_grad=True)
        >>> with torch.no_grad():
        ...     embedding.weight[padding_idx] = torch.ones(3)
        >>> embedding.weight
        Parameter containing:
        tensor([[ 1.0000,  1.0000,  1.0000],
                [-0.7895, -0.7089, -0.0364],
                [ 0.6778,  0.5803,  0.2678]], requires_grad=True)
    )