SetFit is an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers. It achieves high accuracy with little labeled data - for instance, with only 8 labeled examples per class on the Customer Reviews sentiment dataset, SetFit is competitive with fine-tuning RoBERTa Large on the full training set of 3k examples.
Features
- Few-shot learning for text classification
- Optimized for efficiency with minimal labeled data
- Uses contrastive learning for improved performance
- Compatible with Hugging Face Transformers
- Works with various sentence embedding models
- Supports rapid fine-tuning and inference
License
Apache License V2.0Follow SetFit
Other Useful Business Software
Earn up to 16% annual interest with Nexo.
Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform.
Geographic restrictions, eligibility, and terms apply.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of SetFit!