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
d588a466
Unverified
Commit
d588a466
authored
Dec 12, 2023
by
Hailey Schoelkopf
Committed by
GitHub
Dec 12, 2023
Browse files
Update vllm_causallms.py
parent
86311c23
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
1 deletion
+3
-1
lm_eval/models/vllm_causallms.py
lm_eval/models/vllm_causallms.py
+3
-1
No files found.
lm_eval/models/vllm_causallms.py
View file @
d588a466
...
...
@@ -150,7 +150,9 @@ please install vllm via `pip install lm-eval[vllm]` or `pip install -e .[vllm]`"
temperature
=
0
,
prompt_logprobs
=
2
,
max_tokens
=
1
)
if
self
.
data_parallel_size
>
1
:
requests
=
[
list
(
x
)
for
x
in
utils
.
divide
(
requests
,
self
.
data_parallel_size
)]
requests
=
[
list
(
x
)
for
x
in
utils
.
divide
(
requests
,
self
.
data_parallel_size
)
]
inputs
=
[(
self
.
model_args
,
sampling_params
,
req
)
for
req
in
requests
]
with
Pool
(
self
.
data_parallel_size
)
as
pool
:
...
...
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