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
003c2581
You need to sign in or sign up before continuing.
Unverified
Commit
003c2581
authored
Jul 09, 2023
by
Lintang Sutawika
Committed by
GitHub
Jul 09, 2023
Browse files
multple_choice handles 2 cases
parent
87d93e99
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
10 additions
and
4 deletions
+10
-4
lm_eval/api/task.py
lm_eval/api/task.py
+10
-4
No files found.
lm_eval/api/task.py
View file @
003c2581
...
@@ -772,19 +772,25 @@ class ConfigurableTask(Task):
...
@@ -772,19 +772,25 @@ class ConfigurableTask(Task):
# TODO: any cleaner way to do this?
# TODO: any cleaner way to do this?
if
self
.
multiple_input
:
if
self
.
multiple_input
:
choices
=
self
.
doc_to_text
(
doc
)
choices
=
self
.
doc_to_text
(
doc
)
continuation
=
self
.
doc_to_target
(
doc
)
cont
=
self
.
doc_to_target
(
doc
)
arguments
=
[
(
ctx
,
" {}"
.
format
(
cont
))
for
ctx
in
choices
]
else
:
else
:
continuation
=
self
.
create_choices
(
doc
)
cont
=
self
.
create_choices
(
doc
)
arguments
=
[
(
ctx
,
" {}"
.
format
(
cont
))
for
cont
in
choices
]
request_list
=
[
request_list
=
[
Instance
(
Instance
(
request_type
=
"loglikelihood"
,
request_type
=
"loglikelihood"
,
doc
=
doc
,
doc
=
doc
,
arguments
=
(
ctx
,
" {}"
.
format
(
choice
))
,
arguments
=
arguments
,
idx
=
i
,
idx
=
i
,
**
kwargs
,
**
kwargs
,
)
)
for
i
,
choice
in
enumerate
(
choice
s
)
for
i
,
arg
in
enumerate
(
argument
s
)
]
]
# TODO: we should raise a warning telling users this will at most ~2x runtime.
# TODO: we should raise a warning telling users this will at most ~2x runtime.
if
"acc_mutual_info"
in
self
.
_metric_fn_list
.
keys
():
if
"acc_mutual_info"
in
self
.
_metric_fn_list
.
keys
():
...
...
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