SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix doc errors and typos across the board (#8139)

Browse Source 
* Fix doc errors and typos across the board

* Fix a typo

* Fix the CI

* Fix more typos

* Fix CI

* More fixes

* Fix CI

* More fixes

* More fixes
This commit is contained in:
Santiago Castro
2020-10-29 10:33:33 -04:00
committed by GitHub
parent 4731a00c3e
commit 969859d5f6
160 changed files with 342 additions and 364 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/deebert/src/modeling_highway_bert.py
View File

@@ -198,7 +198,7 @@ class DeeBertModel(BertPreTrainedModel):
extended_attention_mask: torch.Tensor = self.get_extended_attention_mask(attention_mask, input_shape, device)
# If a 2D ou 3D attention mask is provided for the cross-attention
# we need to make broadcastabe to [batch_size, num_heads, seq_length, seq_length]
# we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
if encoder_attention_mask.dim() == 3:
encoder_extended_attention_mask = encoder_attention_mask[:, None, :, :]
if encoder_attention_mask.dim() == 2:
@@ -260,7 +260,7 @@ class BertHighway(nn.Module):
# BertModel
bmodel_output = (pooler_input, pooler_output) + encoder_outputs[1:]
# "return" bodel_output
# "return" bmodel_output
# Dropout and classification
pooled_output = bmodel_output[1]