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
88 additions
and
3 deletions
+88
-3
lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_university.yaml
...ks/arabicmmlu/arabicmmlu_computer_science_university.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_driving_test.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_driving_test.yaml
+1
-1
lm_eval/tasks/arabicmmlu/arabicmmlu_economics_high_school.yaml
...al/tasks/arabicmmlu/arabicmmlu_economics_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_economics_middle_school.yaml
.../tasks/arabicmmlu/arabicmmlu_economics_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_economics_university.yaml
...val/tasks/arabicmmlu/arabicmmlu_economics_university.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge.yaml
+1
-1
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_middle_school.yaml
...rabicmmlu/arabicmmlu_general_knowledge_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_primary_school.yaml
...abicmmlu/arabicmmlu_general_knowledge_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_high_school.yaml
...al/tasks/arabicmmlu/arabicmmlu_geography_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_middle_school.yaml
.../tasks/arabicmmlu/arabicmmlu_geography_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_primary_school.yaml
...tasks/arabicmmlu/arabicmmlu_geography_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_history_high_school.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_history_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_history_middle_school.yaml
...al/tasks/arabicmmlu/arabicmmlu_history_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_history_primary_school.yaml
...l/tasks/arabicmmlu/arabicmmlu_history_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies.yaml
+1
-1
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_high_school.yaml
...ks/arabicmmlu/arabicmmlu_islamic_studies_high_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_middle_school.yaml
.../arabicmmlu/arabicmmlu_islamic_studies_middle_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_primary_school.yaml
...arabicmmlu/arabicmmlu_islamic_studies_primary_school.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_law_professional.yaml
lm_eval/tasks/arabicmmlu/arabicmmlu_law_professional.yaml
+5
-0
lm_eval/tasks/arabicmmlu/arabicmmlu_management_university.yaml
...al/tasks/arabicmmlu/arabicmmlu_management_university.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_
middle_
computer_science.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science
_university
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Middle
Computer
Science"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
dataset_name"
:
"
Computer
Science
(University)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_computer_science"
"
task_alias"
:
"
Middle
Computer
Science"
"
tag"
:
"
arabicmmlu_stem_tasks"
"
task"
:
"
arabicmmlu_computer_science_university"
"
task_alias"
:
"
Computer
Science
(University)"
lm_eval/tasks/arabicmmlu/arabicmmlu_driving_test.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Driving
Test"
"
tag"
:
"
arabicmmlu_other_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_other_tasks"
"
task"
:
"
arabicmmlu_driving_test"
"
task_alias"
:
"
Driving
Test"
lm_eval/tasks/arabicmmlu/arabicmmlu_economics_high_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Economics
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_economics_high_school"
"
task_alias"
:
"
Economics
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_economics_middle_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Economics
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_economics_middle_school"
"
task_alias"
:
"
Economics
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_
high_civics
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_
economics_university
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
High
Civics"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
dataset_name"
:
"
Economics
(University)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_high_civics"
"
task_alias"
:
"
High
Civics"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_economics_university"
"
task_alias"
:
"
Economics
(University)"
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
General
Knowledge"
"
tag"
:
"
arabicmmlu_other_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_other_tasks"
"
task"
:
"
arabicmmlu_general_knowledge"
"
task_alias"
:
"
General
Knowledge"
lm_eval/tasks/arabicmmlu/arabicmmlu_
middle_
general_knowledge.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge
_middle_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Middle
General
Knowledge"
"
tag"
:
"
arabicmmlu_other_tasks"
"
dataset_name"
:
"
General
Knowledge
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_general_knowledge"
"
task_alias"
:
"
Middle
General
Knowledge"
"
tag"
:
"
arabicmmlu_other_tasks"
"
task"
:
"
arabicmmlu_general_knowledge_middle_school"
"
task_alias"
:
"
General
Knowledge
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_
primary_
general_knowledge.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge
_primary_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Primary
General
Knowledge"
"
tag"
:
"
arabicmmlu_other_tasks"
"
dataset_name"
:
"
General
Knowledge
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_primary_general_knowledge"
"
task_alias"
:
"
Primary
General
Knowledge"
"
tag"
:
"
arabicmmlu_other_tasks"
"
task"
:
"
arabicmmlu_general_knowledge_primary_school"
"
task_alias"
:
"
General
Knowledge
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_high_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Geography
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_geography_high_school"
"
task_alias"
:
"
Geography
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_middle_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Geography
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_geography_middle_school"
"
task_alias"
:
"
Geography
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_geography_primary_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Geography
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_social_science_tasks"
"
task"
:
"
arabicmmlu_geography_primary_school"
"
task_alias"
:
"
Geography
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_hi
gh_islamic_studies
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_hi
story_high_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
High
Islamic
Studies"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
dataset_name"
:
"
History
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_high_islamic_studies"
"
task_alias"
:
"
High
Islamic
Studies"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_history_high_school"
"
task_alias"
:
"
History
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_hi
gh_philosophy
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_hi
story_middle_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
High
Philosophy"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
dataset_name"
:
"
History
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_high_philosophy"
"
task_alias"
:
"
High
Philosophy"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_history_middle_school"
"
task_alias"
:
"
History
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_
middle_
history.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_history
_primary_school
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Middle
History"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
dataset_name"
:
"
History
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_middle_history"
"
task_alias"
:
"
Middle
History"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_history_primary_school"
"
task_alias"
:
"
History
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Islamic
Studies"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_islamic_studies"
"
task_alias"
:
"
Islamic
Studies"
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_high_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Islamic
Studies
(High
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_islamic_studies_high_school"
"
task_alias"
:
"
Islamic
Studies
(High
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_middle_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Islamic
Studies
(Middle
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_islamic_studies_middle_school"
"
task_alias"
:
"
Islamic
Studies
(Middle
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_primary_school.yaml
0 → 100644
View file @
89b6bdb3
"
dataset_name"
:
"
Islamic
Studies
(Primary
School)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_islamic_studies_primary_school"
"
task_alias"
:
"
Islamic
Studies
(Primary
School)"
lm_eval/tasks/arabicmmlu/arabicmmlu_
high_history
.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_
law_professional
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
High
History"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
dataset_name"
:
"
Law
(Professional)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_high_history"
"
task_alias"
:
"
High
History"
"
tag"
:
"
arabicmmlu_humanities_tasks"
"
task"
:
"
arabicmmlu_law_professional"
"
task_alias"
:
"
Law
(Professional)"
lm_eval/tasks/arabicmmlu/arabicmmlu_
univ_
management.yaml
→
lm_eval/tasks/arabicmmlu/arabicmmlu_management
_university
.yaml
View file @
89b6bdb3
"
dataset_name"
:
"
Univ
Management"
"
tag"
:
"
arabicmmlu_other_tasks"
"
dataset_name"
:
"
Management
(University)"
"
include"
:
"
_default_arabicmmlu_template_yaml"
"
task"
:
"
arabicmmlu_univ_management"
"
task_alias"
:
"
Univ
Management"
"
tag"
:
"
arabicmmlu_other_tasks"
"
task"
:
"
arabicmmlu_management_university"
"
task_alias"
:
"
Management
(University)"
Prev
1
2
3
4
5
6
7
8
…
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