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
cc572624
Commit
cc572624
authored
Dec 06, 2023
by
lintangsutawika
Browse files
add style 01
parent
50df117b
Changes
175
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
91 additions
and
0 deletions
+91
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_marketing.yaml
...mlu/alternative_worlds/style_01/a/style_01_marketing.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_medical_genetics.yaml
...ernative_worlds/style_01/a/style_01_medical_genetics.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_miscellaneous.yaml
...alternative_worlds/style_01/a/style_01_miscellaneous.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_moral_disputes.yaml
...lternative_worlds/style_01/a/style_01_moral_disputes.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_moral_scenarios.yaml
...ternative_worlds/style_01/a/style_01_moral_scenarios.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_nutrition.yaml
...mlu/alternative_worlds/style_01/a/style_01_nutrition.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_philosophy.yaml
...lu/alternative_worlds/style_01/a/style_01_philosophy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_prehistory.yaml
...lu/alternative_worlds/style_01/a/style_01_prehistory.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_accounting.yaml
...e_worlds/style_01/a/style_01_professional_accounting.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_law.yaml
...ernative_worlds/style_01/a/style_01_professional_law.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_medicine.yaml
...ive_worlds/style_01/a/style_01_professional_medicine.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_psychology.yaml
...e_worlds/style_01/a/style_01_professional_psychology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_public_relations.yaml
...ernative_worlds/style_01/a/style_01_public_relations.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_security_studies.yaml
...ernative_worlds/style_01/a/style_01_security_studies.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_sociology.yaml
...mlu/alternative_worlds/style_01/a/style_01_sociology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_us_foreign_policy.yaml
...rnative_worlds/style_01/a/style_01_us_foreign_policy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_virology.yaml
...mmlu/alternative_worlds/style_01/a/style_01_virology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_world_religions.yaml
...ternative_worlds/style_01/a/style_01_world_religions.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/b/_template_yaml
...l/tasks/mmlu/alternative_worlds/style_01/b/_template_yaml
+15
-0
lm_eval/tasks/mmlu/alternative_worlds/style_01/b/style_01_abstract_algebra.yaml
...ernative_worlds/style_01/b/style_01_abstract_algebra.yaml
+4
-0
No files found.
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_marketing.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_marketing"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_medical_genetics.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
genetics.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_medical_genetics"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_miscellaneous.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_miscellaneous"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_moral_disputes.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
disputes.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_moral_disputes"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_moral_scenarios.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
scenarios.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_moral_scenarios"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_nutrition.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_nutrition"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_philosophy.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_philosophy"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_prehistory.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_prehistory"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_accounting.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
accounting.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_professional_accounting"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_law.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
law.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_professional_law"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_medicine.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
medicine.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_professional_medicine"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_professional_psychology.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
psychology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_professional_psychology"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_public_relations.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
relations.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_public_relations"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_security_studies.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
studies.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_security_studies"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_sociology.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_sociology"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_us_foreign_policy.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
foreign
policy.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_us_foreign_policy"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_virology.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_virology"
lm_eval/tasks/mmlu/alternative_worlds/style_01/a/style_01_world_religions.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
religions.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01a_world_religions"
lm_eval/tasks/mmlu/alternative_worlds/style_01/b/_template_yaml
0 → 100644
View file @
cc572624
group: mmlu_style_01
group_alias: style_01
task: mmlu_style_01b
task_alias: b
dataset_path: cais/mmlu
test_split: test
fewshot_split: dev
output_type: multiple_choice
doc_to_text: !function ../../styles.template_01
doc_to_choice: !function ../../styles.choice_01b
doc_to_target: answer
metric_list:
- metric: acc
- metric: acc_norm
- metric: brier_score
lm_eval/tasks/mmlu/alternative_worlds/style_01/b/style_01_abstract_algebra.yaml
0 → 100644
View file @
cc572624
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
algebra.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_01b_abstract_algebra"
Prev
1
2
3
4
5
6
7
…
9
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