SaT Base Models Base SaT (Segment any Text) models, to be used for sentence and paragraph segmentation. Easily adaptable via LoRA. segment-any-text/sat-1l Token Classification • Updated Sep 24, 2024 • 150 • 1 segment-any-text/sat-3l Token Classification • Updated Sep 24, 2024 • 20.5k • • 4 segment-any-text/sat-6l Token Classification • Updated Sep 24, 2024 • 19 segment-any-text/sat-9l Token Classification • Updated Sep 24, 2024 • 17
SaT Supervised Mixture (SM) Models SaT (Segment any Text) models, further trained on a Supervised Mixture of diverse styles and corruptions. Universal Sentence Segmentation models! segment-any-text/sat-1l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 611 segment-any-text/sat-3l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 125k • • 10 segment-any-text/sat-6l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 809 • • 3 segment-any-text/sat-9l-sm Token Classification • 0.3B • Updated Sep 24, 2024 • 4
SaT Base Models Base SaT (Segment any Text) models, to be used for sentence and paragraph segmentation. Easily adaptable via LoRA. segment-any-text/sat-1l Token Classification • Updated Sep 24, 2024 • 150 • 1 segment-any-text/sat-3l Token Classification • Updated Sep 24, 2024 • 20.5k • • 4 segment-any-text/sat-6l Token Classification • Updated Sep 24, 2024 • 19 segment-any-text/sat-9l Token Classification • Updated Sep 24, 2024 • 17
SaT Supervised Mixture (SM) Models SaT (Segment any Text) models, further trained on a Supervised Mixture of diverse styles and corruptions. Universal Sentence Segmentation models! segment-any-text/sat-1l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 611 segment-any-text/sat-3l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 125k • • 10 segment-any-text/sat-6l-sm Token Classification • 0.2B • Updated Sep 24, 2024 • 809 • • 3 segment-any-text/sat-9l-sm Token Classification • 0.3B • Updated Sep 24, 2024 • 4
