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
0d5748b7
"mmdet/vscode:/vscode.git/clone" did not exist on "e5f6a32ac7259b77314f129839564a12d7142a2d"
Commit
0d5748b7
authored
Dec 13, 2023
by
lintangsutawika
Browse files
added mmlu alt world prompts
parent
b9e55312
Changes
891
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
125 additions
and
0 deletions
+125
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_security_studies.yaml
...ds/output_variation/style_01/a/mmlu_security_studies.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_sociology.yaml
...ve_worlds/output_variation/style_01/a/mmlu_sociology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_us_foreign_policy.yaml
...s/output_variation/style_01/a/mmlu_us_foreign_policy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_virology.yaml
...ive_worlds/output_variation/style_01/a/mmlu_virology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_world_religions.yaml
...lds/output_variation/style_01/a/mmlu_world_religions.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/_mmlu.yaml
...alternative_worlds/output_variation/style_01/b/_mmlu.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/_template_yaml
...rnative_worlds/output_variation/style_01/b/_template_yaml
+11
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_abstract_algebra.yaml
...ds/output_variation/style_01/b/mmlu_abstract_algebra.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_anatomy.yaml
...tive_worlds/output_variation/style_01/b/mmlu_anatomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_astronomy.yaml
...ve_worlds/output_variation/style_01/b/mmlu_astronomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_business_ethics.yaml
...lds/output_variation/style_01/b/mmlu_business_ethics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_clinical_knowledge.yaml
.../output_variation/style_01/b/mmlu_clinical_knowledge.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_biology.yaml
...lds/output_variation/style_01/b/mmlu_college_biology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_chemistry.yaml
...s/output_variation/style_01/b/mmlu_college_chemistry.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_computer_science.yaml
...t_variation/style_01/b/mmlu_college_computer_science.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_mathematics.yaml
...output_variation/style_01/b/mmlu_college_mathematics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_medicine.yaml
...ds/output_variation/style_01/b/mmlu_college_medicine.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_physics.yaml
...lds/output_variation/style_01/b/mmlu_college_physics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_computer_security.yaml
...s/output_variation/style_01/b/mmlu_computer_security.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_conceptual_physics.yaml
.../output_variation/style_01/b/mmlu_conceptual_physics.yaml
+6
-0
No files found.
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_security_studies.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_security_studies"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_sociology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01a_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_sociology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_us_foreign_policy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_us_foreign_policy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_virology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01a_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_virology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_world_religions.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_world_religions"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/_mmlu.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_01b
task
:
-
mmlu_alt_ov_01b_stem
-
mmlu_alt_ov_01b_other
-
mmlu_alt_ov_01b_social_sciences
-
mmlu_alt_ov_01b_humanities
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/_template_yaml
0 → 100644
View file @
0d5748b7
dataset_path: hails/mmlu_no_train
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/output_variation/style_01/b/mmlu_abstract_algebra.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_abstract_algebra"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_anatomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_anatomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_astronomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_astronomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_business_ethics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_business_ethics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_clinical_knowledge.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_clinical_knowledge"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_biology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_biology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_chemistry.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_chemistry"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_computer_science.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_computer_science"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_mathematics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_mathematics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_medicine.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_medicine"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_college_physics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_college_physics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_computer_security.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_computer_security"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/b/mmlu_conceptual_physics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
conceptual_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01b_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01b_conceptual_physics"
Prev
1
2
3
4
5
6
7
8
…
45
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