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
89b6bdb3
Commit
89b6bdb3
authored
Feb 06, 2025
by
Baber
Browse files
Merge branch 'main' into ai2d
parents
59053d58
144a1e58
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
40 additions
and
60 deletions
+40
-60
lm_eval/tasks/arabicmmlu/arabicmmlu_math_primary_school.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_math_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_economics.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_economics.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_geography.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_geography.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_islamic_studies.yaml
...l/tasks/arabicmmlu/arabicmmlu_middle_islamic_studies.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_natural_science.yaml
...l/tasks/arabicmmlu/arabicmmlu_middle_natural_science.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_social_science.yaml
...al/tasks/arabicmmlu/arabicmmlu_middle_social_science.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_natural_science_middle_school.yaml
.../arabicmmlu/arabicmmlu_natural_science_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_natural_science_primary_school.yaml
...arabicmmlu/arabicmmlu_natural_science_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_philosophy_high_school.yaml
...l/tasks/arabicmmlu/arabicmmlu_philosophy_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_physics_high_school.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_physics_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_political_science_university.yaml
...s/arabicmmlu/arabicmmlu_political_science_university.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_computer_science.yaml
...tasks/arabicmmlu/arabicmmlu_primary_computer_science.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_geography.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_geography.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_history.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_history.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_islamic_studies.yaml
.../tasks/arabicmmlu/arabicmmlu_primary_islamic_studies.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_natural_science.yaml
.../tasks/arabicmmlu/arabicmmlu_primary_natural_science.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_social_science.yaml
...l/tasks/arabicmmlu/arabicmmlu_primary_social_science.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_prof_law.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_prof_law.yaml
+0
-5
lm_eval/tasks/arabicmmlu/arabicmmlu_social_science_middle_school.yaml
...s/arabicmmlu/arabicmmlu_social_science_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_social_science_primary_school.yaml
.../arabicmmlu/arabicmmlu_social_science_primary_school.yaml
+5
-0
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
lm_eval/tasks/arabicmmlu/arabicmmlu_
high_biology
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_
math_primary_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
High
Biology"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
dataset_name"
:
"
Math
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_high_biology"
"
task_alias"
:
"
High
Biology"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
task"
:
"
arabicmmlu_math_primary_school"
"
task_alias"
:
"
Math
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_economics.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Middle
Economics"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_economics"
"
task_alias"
:
"
Middle
Economics"
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_geography.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Middle
Geography"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_geography"
"
task_alias"
:
"
Middle
Geography"
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_islamic_studies.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Middle
Islamic
Studies"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_islamic_studies"
"
task_alias"
:
"
Middle
Islamic
Studies"
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_natural_science.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Middle
Natural
Science"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_natural_science"
"
task_alias"
:
"
Middle
Natural
Science"
lm_eval/tasks/arabicmmlu/arabicmmlu_middle_social_science.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Middle
Social
Science"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_social_science"
"
task_alias"
:
"
Middle
Social
Science"
lm_eval/tasks/arabicmmlu/arabicmmlu_natural_science_middle_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Natural
Science
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
task"
:
"
arabicmmlu_natural_science_middle_school"
"
task_alias"
:
"
Natural
Science
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_natural_science_primary_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Natural
Science
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
task"
:
"
arabicmmlu_natural_science_primary_school"
"
task_alias"
:
"
Natural
Science
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_philosophy_high_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Philosophy
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_philosophy_high_school"
"
task_alias"
:
"
Philosophy
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_p
rimary_math
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_p
hysics_high_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Primary
Math"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
dataset_name"
:
"
Physics
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_math"
"
task_alias"
:
"
Primary
Math"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
task"
:
"
arabicmmlu_physics_high_school"
"
task_alias"
:
"
Physics
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_political_science_university.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Political
Science
(University)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_political_science_university"
"
task_alias"
:
"
Political
Science
(University)"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_computer_science.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
Computer
Science"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_computer_science"
"
task_alias"
:
"
Primary
Computer
Science"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_geography.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
Geography"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_geography"
"
task_alias"
:
"
Primary
Geography"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_history.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
History"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_history"
"
task_alias"
:
"
Primary
History"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_islamic_studies.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
Islamic
Studies"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_islamic_studies"
"
task_alias"
:
"
Primary
Islamic
Studies"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_natural_science.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
Natural
Science"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_natural_science"
"
task_alias"
:
"
Primary
Natural
Science"
lm_eval/tasks/arabicmmlu/arabicmmlu_primary_social_science.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Primary
Social
Science"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_social_science"
"
task_alias"
:
"
Primary
Social
Science"
lm_eval/tasks/arabicmmlu/arabicmmlu_prof_law.yaml
deleted
100644 → 0
View file @
59053d58
"
dataset_name"
:
"
Prof
Law"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_prof_law"
"
task_alias"
:
"
Prof
Law"
lm_eval/tasks/arabicmmlu/arabicmmlu_social_science_middle_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Social
Science
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_social_science_middle_school"
"
task_alias"
:
"
Social
Science
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_social_science_primary_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Social
Science
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_social_science_primary_school"
"
task_alias"
:
"
Social
Science
(Primary
School)"
Prev
1
2
3
4
5
6
7
8
9
…
50
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