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

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow SetFit

SetFit Web Site

Other Useful Business Software
Fully Managed MySQL, PostgreSQL, and SQL Server Icon
Fully Managed MySQL, PostgreSQL, and SQL Server

Automatic backups, patching, replication, and failover. Focus on your app, not your database.

Cloud SQL handles your database ops end to end, so you can focus on your app.
Try Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of SetFit!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

Python

Related Categories

Python Natural Language Processing (NLP) Tool, Python LLM Inference Tool

Registered

2025-01-22