saymrwulf/transformers
1
0
Fork 0
mirror of https://github.com/saymrwulf/transformers.git synced 2026-05-14 20:58:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Correct NATTEN function signatures and force new version (#22298)

Browse source
This commit is contained in:
Ali Hassani 2023-03-21 14:21:34 -07:00 committed by GitHub
parent d35f729649
commit 5990743fdd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
setup.py
View file

@ -129,7 +129,7 @@ _deps = [
"keras-nlp>=0.3.1",
"librosa",
"nltk",
"natten>=0.14.5",
"natten>=0.14.6",
"numpy>=1.17",
"onnxconverter-common",
"onnxruntime-tools>=1.4.2",

2
src/transformers/dependency_versions_table.py
View file

@ -35,7 +35,7 @@ deps = {
"keras-nlp": "keras-nlp>=0.3.1",
"librosa": "librosa",
"nltk": "nltk",
"natten": "natten>=0.14.5",
"natten": "natten>=0.14.6",
"numpy": "numpy>=1.17",
"onnxconverter-common": "onnxconverter-common",
"onnxruntime-tools": "onnxruntime-tools>=1.4.2",

2
src/transformers/models/dinat/modeling_dinat.py
View file

@ -356,7 +356,7 @@ class NeighborhoodAttention(nn.Module):
# seem a bit unusual, but is taken from the original Transformer paper.
attention_probs = self.dropout(attention_probs)
context_layer = natten2dav(attention_probs, value_layer, self.dilation)
context_layer = natten2dav(attention_probs, value_layer, self.kernel_size, self.dilation)
context_layer = context_layer.permute(0, 2, 3, 1, 4).contiguous()
new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
context_layer = context_layer.view(new_context_layer_shape)

2
src/transformers/models/nat/modeling_nat.py
View file

@ -348,7 +348,7 @@ class NeighborhoodAttention(nn.Module):
# seem a bit unusual, but is taken from the original Transformer paper.
attention_probs = self.dropout(attention_probs)
context_layer = natten2dav(attention_probs, value_layer, 1)
context_layer = natten2dav(attention_probs, value_layer, self.kernel_size, 1)
context_layer = context_layer.permute(0, 2, 3, 1, 4).contiguous()
new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
context_layer = context_layer.view(new_context_layer_shape)