Merge branch 'typo' of https://github.com/hwijeen/Megatron-LM into github_small_prs

megatron/model/transformer.py

@@ -53,8 +53,7 @@ class ParallelMLP(MegatronModule):
 
     MLP will take the input with h hidden state, project it to 4*h
     hidden dimension, perform nonlinear transformation, and project the
-    state back into h hidden dimension. At the end, dropout is also
-    applied.
+    state back into h hidden dimension.
     """
 
     def __init__(self, init_method, output_layer_init_method):
@@ -84,7 +83,6 @@ class ParallelMLP(MegatronModule):
             init_method=output_layer_init_method,
             skip_bias_add=True)
 
-
     def forward(self, hidden_states):
 
         # [s, b, 4hp]

megatron/mpu/layers.py

@@ -316,8 +316,8 @@ class RowParallelLinear(torch.nn.Module):
         keep_master_weight_for_test: This was added for testing and should be
                                      set to False. It returns the master weights
                                      used for initialization.
-        skip_bias_add: This was added to enable performance optimations where bias
-                       can be fused with other elementwise operations. we skip 
+        skip_bias_add: This was added to enable performance optimization where bias
+                       can be fused with other elementwise operations. We skip
                        adding bias but instead return it.
     """