From 50246f5b9cf7af844f2ecaf3050d96cb6a33be44 Mon Sep 17 00:00:00 2001 From: sekyondaMeta <127536312+sekyondaMeta@users.noreply.github.com> Date: Wed, 13 Aug 2025 09:43:41 -0400 Subject: [PATCH 1/2] Update transformer_building_blocks.py --- intermediate_source/transformer_building_blocks.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/intermediate_source/transformer_building_blocks.py b/intermediate_source/transformer_building_blocks.py index 8b88707004..ade4b9177f 100644 --- a/intermediate_source/transformer_building_blocks.py +++ b/intermediate_source/transformer_building_blocks.py @@ -71,7 +71,7 @@ # =============================== # First, we will briefly introduce the four technologies mentioned in the introduction # -# * `torch.nested `_ +# * `torch.nested `_ # # Nested tensors generalize the shape of regular dense tensors, allowing for # representation of ragged-sized data with the same tensor UX. In the context of From 624def46bcffc6b6119391ee45625219afdf34f4 Mon Sep 17 00:00:00 2001 From: sekyondaMeta <127536312+sekyondaMeta@users.noreply.github.com> Date: Wed, 13 Aug 2025 09:46:15 -0400 Subject: [PATCH 2/2] Update transformer_building_blocks.py --- intermediate_source/transformer_building_blocks.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/intermediate_source/transformer_building_blocks.py b/intermediate_source/transformer_building_blocks.py index ade4b9177f..df2fb90f96 100644 --- a/intermediate_source/transformer_building_blocks.py +++ b/intermediate_source/transformer_building_blocks.py @@ -157,7 +157,7 @@ # skipped, performance and memory usage improve. # # We'll demonstrate the above by building upon the ``MultiheadAttention`` layer in the -# `Nested Tensor tutorial `_ +# `Nested Tensor tutorial `_ # and comparing it to the ``nn.MultiheadAttention`` layer. import torch