fix add broadcasted backward grad wrong values

norch/autograd/functions.py

@@ -132,7 +132,7 @@ class SumBackward:
         self.keepdim = keepdim
 
     def backward(self, gradient):
-        input_shape = self.input[0].shape
+        input_shape = self.input[0].shape.copy()
         if self.axis == -1:
             # If axis is None, sum reduces the tensor to a scalar.
             grad_output = float(gradient.tensor.contents.data[0]) * self.input[0].ones_like()

norch/nn/modules/linear.py

@@ -2,15 +2,23 @@ from ..module import Module
 from ..parameter import Parameter
 
 class Linear(Module):
-    def __init__(self, input_dim, output_dim):
+    def __init__(self, input_dim, output_dim, bias=True):
         super().__init__()
         self.input_dim = input_dim
         self.output_dim = output_dim
         self.weight = Parameter(shape=[self.output_dim, self.input_dim])
-        self.bias = Parameter(shape=[self.output_dim, 1])
+
+        if bias:
+            self.bias = Parameter(shape=[self.output_dim, 1])
+        else:
+            self.bias = None
 
     def forward(self, x):
-        z = self.weight @ x + self.bias
+        if self.bias:
+            z = self.weight @ x + self.bias
+        else:
+            z = self.weight @ x
+
         return z
 
     def inner_repr(self):