AI agents now fine-tune SetFit classifiers from a few dozen examples on HF Jobs
tomaarsen · x · 2026-09-08
Daniel van Strien shares a practical recipe: SetFit trains small text classifiers from only a few labeled examples per class, and you can hand the examples plus the recipe to an AI agent to train and evaluate the classifier automatically on Hugging Face Jobs.
The accompanying uv-scripts/classification dataset ships full scripts (train-classifier.py, train-setfit.py), covering both standard encoder fine-tuning and few-shot SetFit, with notes on picking longer-context bodies, pair-count blowup with many classes, and a worked real-world failure case. tomaarsen endorses using AI to orchestrate training of domain-specific encoders this way.
More from coding & agent
- Gergely Orosz: Local agents launching apps on my desktop need to move to VMs or the cloud — rseroter · 2026-09-08
- An agent skill pushes Blender-generated 3D worlds straight to the Hugging Face Hub — mervenoyann · 2026-09-08
- Kimi K3 detects concurrent file edits, pauses to ask user — who was the human himself — serious_mehta · 2026-09-08
- Ethan Mollick let GPT-6 Astra autonomously build his second brain over 5 days — tomcrawshaw01 · 2026-09-08
- OpenAI revamps Codex use cases page with suggested workflows — umesh_ai · 2026-09-08
- Same prompt, different philosophies: Fable 5.1 ships 992 sprite frames vs GPT-6 Astra's 16-pose sheet — bobo-the-merciful · 2026-09-08