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
b1ba4e71
Commit
b1ba4e71
authored
Oct 16, 2023
by
lintangsutawika
Browse files
added alt worlds prompts
parent
2afe7770
Changes
582
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/full_continuation/style_04/style_04_philosophy.yaml
...orlds/full_continuation/style_04/style_04_philosophy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_prehistory.yaml
...orlds/full_continuation/style_04/style_04_prehistory.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_accounting.yaml
...ntinuation/style_04/style_04_professional_accounting.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_law.yaml
...full_continuation/style_04/style_04_professional_law.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_medicine.yaml
...continuation/style_04/style_04_professional_medicine.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_psychology.yaml
...ntinuation/style_04/style_04_professional_psychology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_public_relations.yaml
...full_continuation/style_04/style_04_public_relations.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_security_studies.yaml
...full_continuation/style_04/style_04_security_studies.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_sociology.yaml
...worlds/full_continuation/style_04/style_04_sociology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_us_foreign_policy.yaml
...ull_continuation/style_04/style_04_us_foreign_policy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_virology.yaml
..._worlds/full_continuation/style_04/style_04_virology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_world_religions.yaml
.../full_continuation/style_04/style_04_world_religions.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/_template_yaml
...ernative_worlds/full_continuation/style_05/_template_yaml
+15
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_abstract_algebra.yaml
...full_continuation/style_05/style_05_abstract_algebra.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_anatomy.yaml
...e_worlds/full_continuation/style_05/style_05_anatomy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_astronomy.yaml
...worlds/full_continuation/style_05/style_05_astronomy.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_business_ethics.yaml
.../full_continuation/style_05/style_05_business_ethics.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_clinical_knowledge.yaml
...ll_continuation/style_05/style_05_clinical_knowledge.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_college_biology.yaml
.../full_continuation/style_05/style_05_college_biology.yaml
+4
-0
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_college_chemistry.yaml
...ull_continuation/style_05/style_05_college_chemistry.yaml
+4
-0
No files found.
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_philosophy.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_philosophy"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_prehistory.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_prehistory"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_accounting.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
accounting.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_professional_accounting"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_law.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
law.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_professional_law"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_medicine.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
medicine.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_professional_medicine"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_professional_psychology.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
psychology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_professional_psychology"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_public_relations.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
relations.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_public_relations"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_security_studies.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
studies.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_security_studies"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_sociology.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_sociology"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_us_foreign_policy.yaml
0 → 100644
View file @
b1ba4e71
"
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_04_fc_us_foreign_policy"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_virology.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_virology"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_04/style_04_world_religions.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
religions.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_04_fc_world_religions"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/_template_yaml
0 → 100644
View file @
b1ba4e71
group: mmlu_style_05_fc
dataset_path: cais/mmlu
test_split: test
fewshot_split: dev
output_type: multiple_choice
doc_to_text: "Answer the following question with fruit that represents the options: {{question.strip()}}\n(Apple) {{choices[0]}}\n(Banana) {{choices[1]}}\n(Cantaloupe) {{choices[2]}}\n(Durian) {{choices[3]}}\nAnswer: "
doc_to_choice: "{{['(Apple) '+choices[0], '(Banana) '+choices[1], '(Cantaloupe) '+choices[2], '(Durian) '+choices[3]]}}" # "{{choices}}" # ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_abstract_algebra.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
algebra.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_abstract_algebra"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_anatomy.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_anatomy"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_astronomy.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_astronomy"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_business_ethics.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
ethics.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_business_ethics"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_clinical_knowledge.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
knowledge.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_clinical_knowledge"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_college_biology.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
biology.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_college_biology"
lm_eval/tasks/mmlu/alternative_worlds/full_continuation/style_05/style_05_college_chemistry.yaml
0 → 100644
View file @
b1ba4e71
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
chemistry.
\n\n
"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_style_05_fc_college_chemistry"
Prev
1
…
8
9
10
11
12
13
14
15
16
…
30
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