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
f8c2cfcb
Unverified
Commit
f8c2cfcb
authored
Dec 12, 2023
by
Hanwool Albert Lee
Committed by
GitHub
Dec 12, 2023
Browse files
Merge pull request #1089 from h-albert-lee/K-MMLU
Add kmmlu evaluation to tasks
parents
c86f527f
c256eda8
Changes
48
Hide whitespace changes
Inline
Side-by-side
Showing
8 changed files
with
41 additions
and
0 deletions
+41
-0
lm_eval/tasks/kmmlu/kmmlu_public_safety.yaml
lm_eval/tasks/kmmlu/kmmlu_public_safety.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_railway_and_automotive_engineering.yaml
...tasks/kmmlu/kmmlu_railway_and_automotive_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_real_estate.yaml
lm_eval/tasks/kmmlu/kmmlu_real_estate.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_refrigerating_machinery.yaml
lm_eval/tasks/kmmlu/kmmlu_refrigerating_machinery.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_social_welfare.yaml
lm_eval/tasks/kmmlu/kmmlu_social_welfare.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_taxation.yaml
lm_eval/tasks/kmmlu/kmmlu_taxation.yaml
+3
-0
lm_eval/tasks/kmmlu/kmmlu_telecommunications_and_wireless_technology.yaml
...mlu/kmmlu_telecommunications_and_wireless_technology.yaml
+3
-0
lm_eval/tasks/kmmlu/utils.py
lm_eval/tasks/kmmlu/utils.py
+20
-0
No files found.
lm_eval/tasks/kmmlu/kmmlu_public_safety.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Public
Safety"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_public_safety"
lm_eval/tasks/kmmlu/kmmlu_railway_and_automotive_engineering.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Railway
and
Automotive
Engineering"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_railway_and_automotive_engineering"
lm_eval/tasks/kmmlu/kmmlu_real_estate.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Real
Estate"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_real_estate"
lm_eval/tasks/kmmlu/kmmlu_refrigerating_machinery.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Refrigerating
Machinery"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_refrigerating_machinery"
lm_eval/tasks/kmmlu/kmmlu_social_welfare.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Social
Welfare"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_social_welfare"
lm_eval/tasks/kmmlu/kmmlu_taxation.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Taxation"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_taxation"
lm_eval/tasks/kmmlu/kmmlu_telecommunications_and_wireless_technology.yaml
0 → 100644
View file @
f8c2cfcb
"
dataset_name"
:
"
Telecommunications
and
Wireless
Technology"
"
include"
:
"
_default_kmmlu_yaml"
"
task"
:
"
kmmlu_telecommunications_and_wireless_technology"
lm_eval/tasks/kmmlu/utils.py
0 → 100644
View file @
f8c2cfcb
import
datasets
def
process_docs
(
dataset
:
datasets
.
Dataset
)
->
datasets
.
Dataset
:
def
_process_doc
(
doc
):
instruction
=
(
f
"다음을 읽고 정답으로 알맞은 것을 고르시요.
\n
"
f
"### Question:
{
doc
[
'question'
]
}
\n
"
f
"### Options:
\n
"
f
"(1)
{
doc
[
'option#1'
]
}
\n
(2)
{
doc
[
'option#2'
]
}
\n
(3)
{
doc
[
'option#3'
]
}
\n
(4)
{
doc
[
'option#4'
]
}
\n
"
f
"### Answer: 주어진 문제의 정답은"
)
out_doc
=
{
"question"
:
instruction
,
"choices"
:
[
"(1)"
,
"(2)"
,
"(3)"
,
"(4)"
],
"gold"
:
int
(
doc
[
"answer"
])
-
1
,
}
return
out_doc
return
dataset
.
map
(
_process_doc
)
Prev
1
2
3
Next
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