setfit

How does this differ from SetFit? Is it just an alternative implementation? I found the HF version pretty effective and it often works well for multilingual classification. I've used it for intent matching and was pleasantly surprised that Polish, German and other translations of our intents tended to work "for free" when training with just English training data! https://github.com/huggingface/setfit

Yes, no zero shot. Few shot is possible for some use cases with setfit: https://github.com/huggingface/setfit and the very recent Fastfit: https://github.com/IBM/fastfit ( https://arxiv.org/pdf/2404.12365 )

https://github.com/huggingface/setfit gets good fine-tuned scores on some downstream tasks with just 8 labeled examples.

I am looking for software to classify documents into 10-20 categories. The documents are about half-screen to screen long. There are some labeled data (about 50-80 labeled documents per category. not 500 per category), so a few-shot learning might be an option. Algorithms used: it might be something like KNearestNeighbor or some ML/Neural networks (transformers? LLM?). Should just do the proper classification. Some restrictions: It should be a "ready to use" pipeline with documentation about training the model, parameter optimization etc. If possible - there should be some way to use this framework/library without Python (I'm not a Python developer) For example, the [1] and [2] allow to use command-line interface for everything - it seems using Python is optional for these frameworks. The SetFit framework (see [3] and [4]) looks quite pr