Getting Error when defining an instance of the LinearRegressionModel class

[Accute9]

I have created the following LinearRegeressionModel class as defined in the course:

class LinearRegressionModel(nn.Module): # <-- almost everything in Pytorch inherets from nn.Module
  def __init__(self):
    super().__init__()
    self.weights = nn.Parameter(torch.randn((1,),
                                            dtype=torch.float,
                                            requires_grad=True
                                            ))
    self.bias = nn.Parameter(torch.randn((1,),
                                         dtpye=torch.float,
                                         requires_grad=True
                                         ))

    # Forward method to define the computation in the model
  def forward(self, x: torch.Tensor) -> torch.Tensor: # x is input data
    return self.weights * x + self.bias

Whenever I try and define an instance of this class, for example:

model = LinearRegressionModel()

I get a weird error message that I don't understand:

TypeError: randn() received an invalid combination of arguments - got (tuple, requires_grad=bool, dtpye=torch.dtype), but expected one of:
 * (tuple of ints size, *, torch.Generator generator, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, torch.Generator generator, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

Can someone help me out?

[Accute9]

Okay, I reloaded the notebok because I geniuinely could not find anything wrong with the class, and it worked. I guess Colab was being weird or something.

[Surya-Abhinai]

There is a typo error in the argument of self.bias fix it from (dtpye = torch.float to dtype = torch.float)

[mrdbourke]

Glad to hear you got it fixed @NonExistentialism (even if it seems like magic!)

And @Surya-Abhinai is correct, the only thing I could see was the typo in the self.bias parameter.