From 5e1d6372026af5385f72ace51540b5e8a1345334 Mon Sep 17 00:00:00 2001 From: Archangel Date: Tue, 21 Oct 2025 12:40:06 +0530 Subject: [PATCH 1/2] Update classification.py Rectified a spelling error --- examples/classification.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/classification.py b/examples/classification.py index c9e9f5bf..28ef0bb7 100644 --- a/examples/classification.py +++ b/examples/classification.py @@ -96,7 +96,7 @@ def _make_dataset(training: bool) -> kd.data.Pipeline: gm.data.FormatText( key=_INPUT_FIELD, template="""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} model""", ), From 220bac40b0a53f573a85e25ac4dcb6ca4a8e363d Mon Sep 17 00:00:00 2001 From: Archangel Date: Tue, 21 Oct 2025 21:00:20 +0530 Subject: [PATCH 2/2] Update classification.py --- examples/classification.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/classification.py b/examples/classification.py index 28ef0bb7..c0b79926 100644 --- a/examples/classification.py +++ b/examples/classification.py @@ -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.