Update README.md (#27)

Fix the sample code so it compiles after the signature of `te.Linear` has changed.
Signed-off-by: nzmora-nvidia <96238833+nzmora-nvidia@users.noreply.github.com>
Signed-off-by: nzmora-nvidia <96238833+nzmora-nvidia@users.noreply.github.com>

README.rst

@@ -48,7 +48,7 @@ Transformer Engine in action:
   hidden_size = 2048
 
   # Initialize model and inputs.
-  model = te.Linear(in_features, out_features, use_bias=True)
+  model = te.Linear(in_features, out_features, bias=True)
   inp = torch.randn(hidden_size, in_features, device="cuda")
 
   # Create FP8 recipe. Note: All input args are optional.