📄 Flan¶

templates.regression.two_texts.similarity.flan

type: OutputQuantizingTemplate
instruction: "Evaluate the similarity between them and classify them into classes from 0-5 as follows:\n0 : The two sentences are completely dissimilar.\n1 : The two sentences are not equivalent, but are on the same topic.\n2 : The two sentences are not equivalent, but share some details.\n3 : The two sentences are roughly equivalent, but some important information differs/missing.\n4 : The two sentences are mostly equivalent, but some unimportant details differ.\n5 : The two sentences are completely equivalent, as they mean the same thing."
input_format: Sentence 1: {text1} Sentence 2: {text2}
output_format: {attribute_value}
quantum: 1
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