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
543617fe
Unverified
Commit
543617fe
authored
Sep 05, 2024
by
Hailey Schoelkopf
Committed by
GitHub
Sep 05, 2024
Browse files
Bump version to v0.4.4 ; Fixes to TMMLUplus (#2280)
parent
7a1614eb
Changes
76
Hide whitespace changes
Inline
Side-by-side
Showing
16 changed files
with
31 additions
and
46 deletions
+31
-46
lm_eval/tasks/tmmluplus/default/tmmluplus_statistics_and_machine_learning.yaml
...us/default/tmmluplus_statistics_and_machine_learning.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
.../tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_three_principles_of_people.yaml
...mluplus/default/tmmluplus_three_principles_of_people.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_traditional_chinese_medicine_clinical_medicine.yaml
...uplus_traditional_chinese_medicine_clinical_medicine.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
...val/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
...sks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
...al/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
...sks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
...sks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
+2
-3
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
.../tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
+2
-3
pyproject.toml
pyproject.toml
+1
-1
No files found.
lm_eval/tasks/tmmluplus/default/tmmluplus_statistics_and_machine_learning.yaml
View file @
543617fe
"
dataset_name"
:
"
statistics_and_machine_learning"
"
dataset_name"
:
"
statistics_and_machine_learning"
"
description"
:
"
以下為統計與機器學習的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為統計與機器學習的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
tag"
:
"
tmmluplus_STEM_tasks"
"
group_alias"
:
"
STEM"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_statistics_and_machine_learning"
"
task"
:
"
tmmluplus_statistics_and_machine_learning"
"
task_alias"
:
"
statistics
and
machine
learning"
"
task_alias"
:
"
statistics
and
machine
learning"
lm_eval/tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
View file @
543617fe
"
dataset_name"
:
"
taiwanese_hokkien"
"
dataset_name"
:
"
taiwanese_hokkien"
"
description"
:
"
以下為閩南語的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為閩南語的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
tag"
:
"
tmmluplus_social_sciences_tasks"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_taiwanese_hokkien"
"
task"
:
"
tmmluplus_taiwanese_hokkien"
"
task_alias"
:
"
taiwanese
hokkien"
"
task_alias"
:
"
taiwanese
hokkien"
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
View file @
543617fe
"
dataset_name"
:
"
taxation"
"
dataset_name"
:
"
taxation"
"
description"
:
"
以下為稅務的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為稅務的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_humanities"
"
tag"
:
"
tmmluplus_humanities_tasks"
"
group_alias"
:
"
humanities"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_taxation"
"
task"
:
"
tmmluplus_taxation"
"
task_alias"
:
"
taxation"
"
task_alias"
:
"
taxation"
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
View file @
543617fe
"
dataset_name"
:
"
technical"
"
dataset_name"
:
"
technical"
"
description"
:
"
以下為技術工相關的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為技術工相關的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_technical"
"
task"
:
"
tmmluplus_technical"
"
task_alias"
:
"
technical"
"
task_alias"
:
"
technical"
lm_eval/tasks/tmmluplus/default/tmmluplus_three_principles_of_people.yaml
View file @
543617fe
"
dataset_name"
:
"
three_principles_of_people"
"
dataset_name"
:
"
three_principles_of_people"
"
description"
:
"
以下為三民主義的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為三民主義的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
tag"
:
"
tmmluplus_social_sciences_tasks"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_three_principles_of_people"
"
task"
:
"
tmmluplus_three_principles_of_people"
"
task_alias"
:
"
three
principles
of
people"
"
task_alias"
:
"
three
principles
of
people"
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
View file @
543617fe
"
dataset_name"
:
"
trade"
"
dataset_name"
:
"
trade"
"
description"
:
"
以下為貿易的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為貿易的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_trade"
"
task"
:
"
tmmluplus_trade"
"
task_alias"
:
"
trade"
"
task_alias"
:
"
trade"
lm_eval/tasks/tmmluplus/default/tmmluplus_traditional_chinese_medicine_clinical_medicine.yaml
View file @
543617fe
"
dataset_name"
:
"
traditional_chinese_medicine_clinical_medicine"
"
dataset_name"
:
"
traditional_chinese_medicine_clinical_medicine"
"
description"
:
"
以下為中醫臨床醫學的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為中醫臨床醫學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_traditional_chinese_medicine_clinical_medicine"
"
task"
:
"
tmmluplus_traditional_chinese_medicine_clinical_medicine"
"
task_alias"
:
"
traditional
chinese
medicine
clinical
medicine"
"
task_alias"
:
"
traditional
chinese
medicine
clinical
medicine"
lm_eval/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
View file @
543617fe
"
dataset_name"
:
"
trust_practice"
"
dataset_name"
:
"
trust_practice"
"
description"
:
"
以下為信託實務的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為信託實務的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_humanities"
"
tag"
:
"
tmmluplus_humanities_tasks"
"
group_alias"
:
"
humanities"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_trust_practice"
"
task"
:
"
tmmluplus_trust_practice"
"
task_alias"
:
"
trust
practice"
"
task_alias"
:
"
trust
practice"
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
View file @
543617fe
"
dataset_name"
:
"
ttqav2"
"
dataset_name"
:
"
ttqav2"
"
description"
:
"
以下為台灣在地用語的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為台灣在地用語的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
tag"
:
"
tmmluplus_social_sciences_tasks"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_ttqav2"
"
task"
:
"
tmmluplus_ttqav2"
"
task_alias"
:
"
ttqav2"
"
task_alias"
:
"
ttqav2"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
View file @
543617fe
"
dataset_name"
:
"
tve_chinese_language"
"
dataset_name"
:
"
tve_chinese_language"
"
description"
:
"
以下為統測國文的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為統測國文的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
tag"
:
"
tmmluplus_social_sciences_tasks"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_chinese_language"
"
task"
:
"
tmmluplus_tve_chinese_language"
"
task_alias"
:
"
tve
chinese
language"
"
task_alias"
:
"
tve
chinese
language"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
View file @
543617fe
"
dataset_name"
:
"
tve_design"
"
dataset_name"
:
"
tve_design"
"
description"
:
"
以下為統測
設計的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為統測
設計的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_design"
"
task"
:
"
tmmluplus_tve_design"
"
task_alias"
:
"
tve
design"
"
task_alias"
:
"
tve
design"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
View file @
543617fe
"
dataset_name"
:
"
tve_mathematics"
"
dataset_name"
:
"
tve_mathematics"
"
description"
:
"
以下為統測數學的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為統測數學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
tag"
:
"
tmmluplus_STEM_tasks"
"
group_alias"
:
"
STEM"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_mathematics"
"
task"
:
"
tmmluplus_tve_mathematics"
"
task_alias"
:
"
tve
mathematics"
"
task_alias"
:
"
tve
mathematics"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
View file @
543617fe
"
dataset_name"
:
"
tve_natural_sciences"
"
dataset_name"
:
"
tve_natural_sciences"
"
description"
:
"
以下為統測自然科的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為統測自然科的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
tag"
:
"
tmmluplus_STEM_tasks"
"
group_alias"
:
"
STEM"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_natural_sciences"
"
task"
:
"
tmmluplus_tve_natural_sciences"
"
task_alias"
:
"
tve
natural
sciences"
"
task_alias"
:
"
tve
natural
sciences"
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
View file @
543617fe
"
dataset_name"
:
"
veterinary_pathology"
"
dataset_name"
:
"
veterinary_pathology"
"
description"
:
"
以下為獸醫病理學的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為獸醫病理學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_veterinary_pathology"
"
task"
:
"
tmmluplus_veterinary_pathology"
"
task_alias"
:
"
veterinary
pathology"
"
task_alias"
:
"
veterinary
pathology"
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
View file @
543617fe
"
dataset_name"
:
"
veterinary_pharmacology"
"
dataset_name"
:
"
veterinary_pharmacology"
"
description"
:
"
以下為獸醫藥理學的單選題,請提供正確答案的選項。
\n\n
"
"
description"
:
"
以下為獸醫藥理學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
tag"
:
"
tmmluplus_other_tasks"
"
group_alias"
:
"
other"
"
include"
:
"
_tmmluplus_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_veterinary_pharmacology"
"
task"
:
"
tmmluplus_veterinary_pharmacology"
"
task_alias"
:
"
veterinary
pharmacology"
"
task_alias"
:
"
veterinary
pharmacology"
pyproject.toml
View file @
543617fe
...
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
...
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project]
[project]
name
=
"lm_eval"
name
=
"lm_eval"
version
=
"0.4.
3
"
version
=
"0.4.
4
"
authors
=
[
authors
=
[
{name=
"EleutherAI"
,
email=
"contact@eleuther.ai"
}
{name=
"EleutherAI"
,
email=
"contact@eleuther.ai"
}
]
]
...
...
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