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
gaoqiong
lm-evaluation-harness
Commits
61b63da7
".github/vscode:/vscode.git/clone" did not exist on "a8c5413d06b417f9484d8723da308215a7eed922"
Unverified
Commit
61b63da7
authored
Mar 20, 2025
by
Yifei Zhang
Committed by
GitHub
Mar 20, 2025
Browse files
Configure the pad tokens for Qwen when using vLLM (#2810)
parent
7158f4f4
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
5 deletions
+5
-5
lm_eval/models/vllm_causallms.py
lm_eval/models/vllm_causallms.py
+5
-5
No files found.
lm_eval/models/vllm_causallms.py
View file @
61b63da7
...
...
@@ -125,7 +125,7 @@ class VLLM(TemplateLM):
revision
=
tokenizer_revision
,
add_bos_token
=
add_bos_token
,
)
self
.
tokenizer
=
configure_pad_token
(
self
.
tokenizer
)
self
.
tokenizer
=
configure_pad_token
(
self
.
tokenizer
,
model_config
=
self
.
_config
)
self
.
add_bos_token
=
add_bos_token
if
"gemma"
in
pretrained
.
lower
():
self
.
add_bos_token
=
True
...
...
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