Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenpangpang
transformers
Commits
cae641ff
Unverified
Commit
cae641ff
authored
Dec 04, 2019
by
Thomas Wolf
Committed by
GitHub
Dec 04, 2019
Browse files
Merge pull request #1846 from tamuhey/patch/iss1845
fix summary_type value of SequenceSummary
parents
7edb51f3
d08a338c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
transformers/modeling_utils.py
transformers/modeling_utils.py
+1
-1
No files found.
transformers/modeling_utils.py
View file @
cae641ff
...
@@ -740,7 +740,7 @@ class SequenceSummary(nn.Module):
...
@@ -740,7 +740,7 @@ class SequenceSummary(nn.Module):
def
__init__
(
self
,
config
):
def
__init__
(
self
,
config
):
super
(
SequenceSummary
,
self
).
__init__
()
super
(
SequenceSummary
,
self
).
__init__
()
self
.
summary_type
=
config
.
summary_type
if
hasattr
(
config
,
'summary_
use_proj
'
)
else
'last'
self
.
summary_type
=
config
.
summary_type
if
hasattr
(
config
,
'summary_
type
'
)
else
'last'
if
self
.
summary_type
==
'attn'
:
if
self
.
summary_type
==
'attn'
:
# We should use a standard multi-head attention module with absolute positional embedding for that.
# We should use a standard multi-head attention module with absolute positional embedding for that.
# Cf. https://github.com/zihangdai/xlnet/blob/master/modeling.py#L253-L276
# Cf. https://github.com/zihangdai/xlnet/blob/master/modeling.py#L253-L276
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment