Skip to content

Update classification.py #435

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
DemonJuanWatermelon wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update classification.py #435

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e1d637
Update classification.py
DemonJuanWatermelon Oct 21, 2025
220bac4
Update classification.py
DemonJuanWatermelon Oct 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions examples/classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def _make_dataset(training: bool) -> kd.data.Pipeline:
gm.data.FormatText(
key=_INPUT_FIELD,
template="""<start_of_turn>user
Please classify whether the following sentence is grammaticaly correct, please answer only with Yes or No.
Please classify whether the following sentence is grammatically correct, please answer only with Yes or No.
Sentence: {text}<end_of_turn>
<start_of_turn>model""",
),
Expand All @@ -113,7 +113,7 @@ def _make_dataset(training: bool) -> kd.data.Pipeline:
gm.data.MapInts(
key=_LABEL_FIELD,
# Rather than predicting the token 0 and 1, we are using the
# token 1294 and 3553 which respectivelly correspond to "No" and
# token 1294 and 3553 which respectively correspond to "No" and
# "Yes". We do this because those token already contain semantic
# information, so even zero-shot prediction without any
# finetuning has better than random performances.
Expand Down