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
90ad5db7
Commit
90ad5db7
authored
Mar 01, 2024
by
lintangsutawika
Browse files
merged main
parents
f692caa9
b177c82c
Changes
484
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
60 additions
and
0 deletions
+60
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_electrical_engineering.yaml
...direct_hard/kmmlu_direct_hard_electrical_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_electronics_engineering.yaml
...irect_hard/kmmlu_direct_hard_electronics_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_energy_management.yaml
...mmlu/direct_hard/kmmlu_direct_hard_energy_management.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_environmental_science.yaml
.../direct_hard/kmmlu_direct_hard_environmental_science.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_fashion.yaml
...al/tasks/kmmlu/direct_hard/kmmlu_direct_hard_fashion.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_food_processing.yaml
.../kmmlu/direct_hard/kmmlu_direct_hard_food_processing.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_gas_technology_and_engineering.yaml
...ard/kmmlu_direct_hard_gas_technology_and_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_geomatics.yaml
.../tasks/kmmlu/direct_hard/kmmlu_direct_hard_geomatics.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_health.yaml
...val/tasks/kmmlu/direct_hard/kmmlu_direct_hard_health.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_industrial_engineer.yaml
...lu/direct_hard/kmmlu_direct_hard_industrial_engineer.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_information_technology.yaml
...direct_hard/kmmlu_direct_hard_information_technology.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_interior_architecture_and_design.yaml
...d/kmmlu_direct_hard_interior_architecture_and_design.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_korean_history.yaml
...s/kmmlu/direct_hard/kmmlu_direct_hard_korean_history.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_law.yaml
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_law.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_machine_design_and_manufacturing.yaml
...d/kmmlu_direct_hard_machine_design_and_manufacturing.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_management.yaml
...tasks/kmmlu/direct_hard/kmmlu_direct_hard_management.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_maritime_engineering.yaml
...u/direct_hard/kmmlu_direct_hard_maritime_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_marketing.yaml
.../tasks/kmmlu/direct_hard/kmmlu_direct_hard_marketing.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_materials_engineering.yaml
.../direct_hard/kmmlu_direct_hard_materials_engineering.yaml
+3
-0
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_math.yaml
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_math.yaml
+3
-0
No files found.
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_electrical_engineering.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
electrical_engineering
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_electrical_engineering
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_electronics_engineering.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
electronics_engineering
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_electronics_engineering
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_energy_management.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
energy_management
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_energy_management
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_environmental_science.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
environmental_science
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_environmental_science
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_fashion.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
fashion
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_fashion
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_food_processing.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
food_processing
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_food_processing
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_gas_technology_and_engineering.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
gas_technology_and_engineering
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_gas_technology_and_engineering
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_geomatics.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
geomatics
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_geomatics
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_health.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
health
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_health
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_industrial_engineer.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
industrial_engineer
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_industrial_engineer
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_information_technology.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
information_technology
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_information_technology
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_interior_architecture_and_design.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
interior_architecture_and_design
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_interior_architecture_and_design
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_korean_history.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
korean_history
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_korean_history
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_law.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
law
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_law
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_machine_design_and_manufacturing.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
machine_design_and_manufacturing
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_machine_design_and_manufacturing
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_management.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
management
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_management
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_maritime_engineering.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
maritime_engineering
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_maritime_engineering
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_marketing.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
marketing
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_marketing
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_materials_engineering.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
materials_engineering
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_materials_engineering
lm_eval/tasks/kmmlu/direct_hard/kmmlu_direct_hard_math.yaml
0 → 100644
View file @
90ad5db7
dataset_name
:
math
include
:
_direct_hard_kmmlu_yaml
task
:
kmmlu_hard_direct_math
Prev
1
…
8
9
10
11
12
13
14
15
16
…
25
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