SetFit v1.2.0 released: prompt-free few-shot classifier catches up with modern stack
Hugging Face's tomaarsen released SetFit v1.2.0 on September 4 — a prompt-free few-shot text classification framework: it constructs positive/negative pairs from a small number of labeled sentences, contrastively fine-tunes a Sentence Transformer, then trains a classification head on the embeddings, requiring no prompts or LLMs. With just 8 samples per class, it can match the performance of fine-tuning RoBERTa-Large with roughly 3,000 samples.
Confirmed
- Fixed ecosystem compatibility issues: failing to import under transformers v5, failing to load Hub models under huggingfacehub v1, Sentence Transformers v5.4+ warning on every import, datasets-related issues, etc. — these defects had left SetFit clearly behind the ecosystem
- Added Python 3.13 support
- Fixed saving failures before training under codecarbon 3.x
- Fixed ONNX/OpenVINO export
- Dependency adjustments: requires evaluate>=0.4.6, as older versions cannot load metrics with huggingfacehub v1
- Included documentation and notebook updates, plus fixes such as dataset ID namespaces
Why it matters
SetFit lets teams without large amounts of labeled data or those who prefer not to rely on LLMs and prompt engineering train competitive text classifiers with just 8 samples per class. Previous versions had become nearly unusable in the current ecosystem due to aging dependencies; v1.2.0 makes it work again on the latest transformers, huggingfacehub, and Sentence Transformers stacks.
2026-09-04 ~ 2026-09-04 · 9 related posts
Primary sources
- [source] SetFit v1.2.0 released with support for transformers v5, Sentence Transformers v6 — tomaarsen · 2026-09-04
- SetFit recap: 8 examples per class rivals RoBERTa-Large fine-tuned on 3k — tomaarsen · 2026-09-04
- SetFit overhauls CI to support transformers v5, huggingface_hub v1 and Python 3.13 — tomaarsen · 2026-09-04
- SetFit v1.2.0 tested across transformers 4.41-5.16, with v5 migration details — tomaarsen · 2026-09-04
- [source] SetFit fixes ONNX export on torch 2.9+ and adds OpenVINO 2026 support — tomaarsen · 2026-09-04
- SetFit v1.2.0 adds Python 3.13 support and dataset ID namespace fixes — tomaarsen · 2026-09-04
- SetFit remains one of the cheapest ways to train solid text classifiers — tomaarsen · 2026-09-04
- [source] SetFit v1.2.0 fixes transformers v5 breakage and ONNX/OpenVINO export — tomaarsen · 2026-09-04
1 near-duplicate retellings: tomaarsen