We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 73375b3 commit 17ca484Copy full SHA for 17ca484
apex/normalization/fused_layer_norm.py
@@ -745,8 +745,7 @@ class FusedLayerNorm(torch.nn.Module):
745
normalize over the last dimension which is expected to be of that specific size.
746
eps: a value added to the denominator for numerical stability. Default: 1e-5
747
elementwise_affine: a boolean value that when set to ``True``, this module
748
- has learnable per-element affine parameters initialized to ones (for weights)
749
- and zeros (for biases). Default: ``True``.
+ has learnable per-element affine parameters initialized to ones for weights. Default: ``True``.
750
751
Shape:
752
- Input: :math:`(N, *)`
0 commit comments