Gemma-APS is a generative model and a research tool for abstractive proposition segmentation (APS for short), a.k.a. claim extraction. Given a text passage, the model segments the content into the individual facts, statements, and ideas expressed in the text, and restates them in full sentences with small changes to the original text.

example:

input: my cat is furry cute and likes to catch mice. He hates dogs and watches the birds

output:

PROPOSITIONS:

The cat is furry cute. The cat likes to catch mice. The cat hates dogs. The cat watches the birds.

source: https://huggingface.co/bartowski/gemma-2b-aps-it-GGUF