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
7d6ec4d9
Commit
7d6ec4d9
authored
Aug 04, 2025
by
Baber
Browse files
Merge branch 'main' into metrics
# Conflicts: # lm_eval/__init__.py # pyproject.toml
parents
1020c46e
d021bf84
Changes
74
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
40 additions
and
40 deletions
+40
-40
lm_eval/tasks/mmlu/continuation/mmlu_high_school_us_history.yaml
.../tasks/mmlu/continuation/mmlu_high_school_us_history.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_world_history.yaml
...sks/mmlu/continuation/mmlu_high_school_world_history.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_human_aging.yaml
lm_eval/tasks/mmlu/continuation/mmlu_human_aging.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml
...tasks/mmlu/continuation/mmlu_professional_accounting.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
...l/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
+2
-2
No files found.
lm_eval/tasks/mmlu/continuation/mmlu_high_school_us_history.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_us_history"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
us
history.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_us_history"
"
task"
:
"
mmlu_high_school_us_history
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_world_history.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_world_history"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
world
history.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_world_history"
"
task"
:
"
mmlu_high_school_world_history
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_human_aging.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
human_aging"
"
description"
:
"
The
following
are
questions
(with
answers)
about
human
\
\
aging.
\n\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation
_human_aging
"
"
task"
:
"
mmlu_
human_aging_
continuation"
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
human_sexuality"
"
description"
:
"
The
following
are
questions
(with
answers)
about
human
\
\
sexuality.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
human_sexuality"
"
task"
:
"
mmlu_human_sexuality
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
international_law"
"
description"
:
"
The
following
are
questions
(with
answers)
about
international
\
\
law.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
international_law"
"
task"
:
"
mmlu_international_law
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
jurisprudence"
"
task"
:
"
mmlu_jurisprudence
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
logical_fallacies"
"
task"
:
"
mmlu_logical_fallacies
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
machine_learning"
"
task"
:
"
mmlu_machine_learning
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
questions
(with
answers)
about
management.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation
_management
"
"
task"
:
"
mmlu_
management_
continuation"
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
questions
(with
answers)
about
marketing.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation
_marketing
"
"
task"
:
"
mmlu_
marketing_
continuation"
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
medical_genetics"
"
task"
:
"
mmlu_medical_genetics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
miscellaneous"
"
task"
:
"
mmlu_miscellaneous
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
moral_disputes"
"
task"
:
"
mmlu_moral_disputes
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
moral_scenarios"
"
task"
:
"
mmlu_moral_scenarios
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_nutri
tion"
"
task"
:
"
mmlu_
nutrition_continua
tion"
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation
_philosophy
"
"
task"
:
"
mmlu_
philosophy_
continuation"
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation
_prehistory
"
"
task"
:
"
mmlu_
prehistory_
continuation"
lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
professional_accounting"
"
task"
:
"
mmlu_professional_accounting
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
professional_law"
"
task"
:
"
mmlu_professional_law
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
professional_medicine"
"
task"
:
"
mmlu_professional_medicine
_continuation
"
Prev
1
2
3
4
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