π TitleΒΆ
templates.regression.single_text.title
OutputQuantizingTemplate
(
instruction="Given a text, on a scale of {min_value} to {max_value}, what is the {attribute_name} of this text?",
input_format="Text:
{text}",
output_format="{attribute_value}",
target_prefix="{attribute_name}:
",
quantum=0.2,
title_fields=[
"attribute_name",
],
postprocessors=[
"processors.take_first_non_empty_line",
"processors.cast_to_float_return_zero_if_failed",
],
)
[source]References: processors.cast_to_float_return_zero_if_failed, processors.take_first_non_empty_line
Read more about catalog usage here.