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
46bd5e46
Commit
46bd5e46
authored
Sep 07, 2023
by
lintangsutawika
Browse files
update
parent
2d530664
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
4 additions
and
4 deletions
+4
-4
lm_eval/tasks/qasper/README.md
lm_eval/tasks/qasper/README.md
+3
-3
lm_eval/tasks/qasper/utils.py
lm_eval/tasks/qasper/utils.py
+1
-1
No files found.
lm_eval/tasks/qasper/README.md
View file @
46bd5e46
...
@@ -42,12 +42,12 @@ Homepage: https://allenai.org/data/qasper
...
@@ -42,12 +42,12 @@ Homepage: https://allenai.org/data/qasper
#### Groups
#### Groups
*
`qasper`
:
`Short description
`
*
`qasper`
:
executes both
`qasper_bool`
and
`qasper_freeform
`
#### Tasks
#### Tasks
*
`qasper_bool`
:
`1-sentence description of what this particular task does`
*
`qasper_bool`
:
Multiple choice task that evaluates the task with
`answer_type="bool"`
*
`qasper_freeform`
:
...
*
`qasper_freeform`
:
Greedy generation task that evaluates the samples from the task with
`answer_type="free form answer"`
### Checklist
### Checklist
...
...
lm_eval/tasks/qasper/utils.py
View file @
46bd5e46
...
@@ -70,4 +70,4 @@ def process_docs(dataset, set_answer_type="bool"):
...
@@ -70,4 +70,4 @@ def process_docs(dataset, set_answer_type="bool"):
return
Dataset
.
from_dict
(
new_dataset
)
return
Dataset
.
from_dict
(
new_dataset
)
process_docs_bool
=
partial
(
process_docs
,
set_answer_type
=
"bool"
)
process_docs_bool
=
partial
(
process_docs
,
set_answer_type
=
"bool"
)
process_docs_freeform
=
partial
(
process_docs
,
set_answer_type
=
"freeform"
)
process_docs_freeform
=
partial
(
process_docs
,
set_answer_type
=
"free
form
answer
"
)
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