SaT Base Models
Collection
Base SaT (Segment any Text) models, to be used for sentence and paragraph segmentation. Easily adaptable via LoRA. โข 6 items โข Updated โข 3
How to use segment-any-text/sat-1l with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("token-classification", model="segment-any-text/sat-1l") # Load model directly
from transformers import AutoModelForTokenClassification
model = AutoModelForTokenClassification.from_pretrained("segment-any-text/sat-1l", dtype="auto")Model for wtpsplit.
State-of-the-art sentence segmentation with 1 Transfomer layer.
For details, see our Segment any Text paper