SetFit doesn’t require large-scale models like T0, Llama or GPT-4 to achieve high accuracy. As a result, it is typically an order of magnitude (or more) faster to train and run inference with.
from setfit import SetFitModel
# Download from 🤗 Hub
model = SetFitModel.from_pretrained("tomaarsen/setfit-all-MiniLM-L6-v2-sst2-8-shot")
# Run inference
preds = model("a fast , funny , highly enjoyable movie . ")
# https://huggingface.co/tomaarsen/setfit-all-MiniLM-L6-v2-sst2-32-shot?text=That%27s+really+awesome%21
