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
3a8f1e44
Unverified
Commit
3a8f1e44
authored
May 10, 2024
by
Jess
Committed by
GitHub
May 10, 2024
Browse files
Merge branch 'EleutherAI:main' into main
parents
cc58abec
1980a13c
Changes
64
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
120 additions
and
0 deletions
+120
-0
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml
...tasks/mmlu/continuation/mmlu_professional_accounting.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
...l/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_professional_psychology.yaml
...tasks/mmlu/continuation/mmlu_professional_psychology.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml
lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml
+6
-0
lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml
lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml
+6
-0
No files found.
lm_eval/tasks/mmlu/continuation/mmlu_human_sexuality.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
human_sexuality"
"
description"
:
"
The
following
are
questions
(with
answers)
about
human
\
\
sexuality.
\n\n
"
"
group"
:
"
mmlu_continuation_social_sciences"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_human_sexuality"
lm_eval/tasks/mmlu/continuation/mmlu_international_law.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
international_law"
"
description"
:
"
The
following
are
questions
(with
answers)
about
international
\
\
law.
\n\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_international_law"
lm_eval/tasks/mmlu/continuation/mmlu_jurisprudence.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_jurisprudence"
lm_eval/tasks/mmlu/continuation/mmlu_logical_fallacies.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_logical_fallacies"
lm_eval/tasks/mmlu/continuation/mmlu_machine_learning.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
group"
:
"
mmlu_continuation_stem"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_machine_learning"
lm_eval/tasks/mmlu/continuation/mmlu_management.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
questions
(with
answers)
about
management.
\n\
\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_management"
lm_eval/tasks/mmlu/continuation/mmlu_marketing.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
questions
(with
answers)
about
marketing.
\n\
\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_marketing"
lm_eval/tasks/mmlu/continuation/mmlu_medical_genetics.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_medical_genetics"
lm_eval/tasks/mmlu/continuation/mmlu_miscellaneous.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_miscellaneous"
lm_eval/tasks/mmlu/continuation/mmlu_moral_disputes.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_moral_disputes"
lm_eval/tasks/mmlu/continuation/mmlu_moral_scenarios.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_moral_scenarios"
lm_eval/tasks/mmlu/continuation/mmlu_nutrition.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_nutrition"
lm_eval/tasks/mmlu/continuation/mmlu_philosophy.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_philosophy"
lm_eval/tasks/mmlu/continuation/mmlu_prehistory.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_prehistory"
lm_eval/tasks/mmlu/continuation/mmlu_professional_accounting.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_professional_accounting"
lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
group"
:
"
mmlu_continuation_humanities"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_professional_law"
lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_continuation_other"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_professional_medicine"
lm_eval/tasks/mmlu/continuation/mmlu_professional_psychology.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
"
group"
:
"
mmlu_continuation_social_sciences"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_professional_psychology"
lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
questions
(with
answers)
about
public
\
\
relations.
\n\n
"
"
group"
:
"
mmlu_continuation_social_sciences"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_public_relations"
lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml
0 → 100644
View file @
3a8f1e44
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_continuation_social_sciences"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_continuation_security_studies"
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