Update

Author: Svetlana Karslioglu

.pyspelling.yml

@@ -22,7 +22,8 @@ matrix:
     #- intermediate_source/nvfuser_intro_tutorial.py
     #- intermediate_source/parametrizations.py
     #- intermediate_source/per_sample_grads.py
-    - intermediate_source/pipeline_tutorial.py
+    #- intermediate_source/pipeline_tutorial.py
+    - intermediate_source/pruning_tutorial.py
   dictionary:
     wordlists:
       - en-wordlist.txt

en-wordlist.txt

@@ -1,3 +1,9 @@
+subnetworks
+sparsify
+LeCun
+prepruned
+dimensionality
+unpruned
 RPC
 multihead
 GPU's

intermediate_source/pipeline_tutorial.py

@@ -35,7 +35,7 @@
 # As a result, our focus is on ``nn.TransformerEncoder`` and we split the model
 # such that half of the ``nn.TransformerEncoderLayer`` are on one GPU and the
 # other half are on another. To do this, we pull out the ``Encoder`` and
-# ``Decoder`` sections into seperate modules and then build an ``nn.Sequential``
+# ``Decoder`` sections into separate modules and then build an ``nn.Sequential``
 # representing the original Transformer module.
 
 import sys
@@ -134,16 +134,17 @@ def forward(self, x):
 # length 6:
 #
 # .. math::
-#   \begin{bmatrix}
-#   \text{A} & \text{B} & \text{C} & \ldots & \text{X} & \text{Y} & \text{Z}
-#   \end{bmatrix}
-#   \Rightarrow
-#   \begin{bmatrix}
-#   \begin{bmatrix}\text{A} \\ \text{B} \\ \text{C} \\ \text{D} \\ \text{E} \\ \text{F}\end{bmatrix} &
-#   \begin{bmatrix}\text{G} \\ \text{H} \\ \text{I} \\ \text{J} \\ \text{K} \\ \text{L}\end{bmatrix} &
-#   \begin{bmatrix}\text{M} \\ \text{N} \\ \text{O} \\ \text{P} \\ \text{Q} \\ \text{R}\end{bmatrix} &
-#   \begin{bmatrix}\text{S} \\ \text{T} \\ \text{U} \\ \text{V} \\ \text{W} \\ \text{X}\end{bmatrix}
-#   \end{bmatrix}
+#
+#    \begin{bmatrix}
+#    \text{A} & \text{B} & \text{C} & \ldots & \text{X} & \text{Y} & \text{Z}
+#    \end{bmatrix}
+#    \Rightarrow
+#    \begin{bmatrix}
+#    \begin{bmatrix}\text{A} \\ \text{B} \\ \text{C} \\ \text{D} \\ \text{E} \\ \text{F}\end{bmatrix} &
+#    \begin{bmatrix}\text{G} \\ \text{H} \\ \text{I} \\ \text{J} \\ \text{K} \\ \text{L}\end{bmatrix} &
+#    \begin{bmatrix}\text{M} \\ \text{N} \\ \text{O} \\ \text{P} \\ \text{Q} \\ \text{R}\end{bmatrix} &
+#    \begin{bmatrix}\text{S} \\ \text{T} \\ \text{U} \\ \text{V} \\ \text{W} \\ \text{X}\end{bmatrix}
+#    \end{bmatrix}
 #
 # These columns are treated as independent by the model, which means that
 # the dependence of ``G`` and ``F`` can not be learned, but allows more

intermediate_source/pruning_tutorial.py

@@ -339,8 +339,8 @@ def forward(self, x):
 # pruning this technique implements (supported options are ``global``,
 # ``structured``, and ``unstructured``). This is needed to determine
 # how to combine masks in the case in which pruning is applied
-# iteratively. In other words, when pruning a pre-pruned parameter,
-# the current prunining techique is expected to act on the unpruned
+# iteratively. In other words, when pruning a prepruned parameter,
+# the current pruning technique is expected to act on the unpruned
 # portion of the parameter. Specifying the ``PRUNING_TYPE`` will
 # enable the ``PruningContainer`` (which handles the iterative
 # application of pruning masks) to correctly identify the slice of the