huggingface/setfit

Efficient few-shot learning with Sentence Transformers

74
/ 100
Verified

Combines pretrained Sentence Transformers with lightweight classification heads (scikit-learn or PyTorch-based) to eliminate the need for prompts or verbalizers in few-shot scenarios. Integrates with Hugging Face Hub for model management and supports multilingual classification through any Sentence Transformer checkpoint. Training uses contrastive learning on minimal labeled examples followed by head fine-tuning, achieving competitive accuracy orders of magnitude faster than large language models.

2,699 stars and 212,684 monthly downloads. Used by 3 other packages. Available on PyPI.

Maintenance 6 / 25
Adoption 23 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

2,699

Forks

255

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Dec 11, 2025

Monthly downloads

212,684

Commits (30d)

0

Dependencies

7

Reverse dependents

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/huggingface/setfit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.