Fine-tuned defect report classifier

The brief

Quality engineers read every defect report to assign a cause. Fine-tune a small open model that runs on the plant's own server to classify reports by cause, and compare it with prompting a large hosted model. Good looks like: a labelled set, a fair test, and a recommendation with accuracy, speed, cost and privacy.

What you will build

1. Build a labelled set of defect reports by cause
2. Fine-tune a small model with LoRA
3. Prompt a large model on the same test set
4. Compare accuracy per cause, speed and cost
5. Recommend one for the plant

Free, open data to build it with

• AI4I 2020 predictive maintenance (failure types) ↗ UCI Machine Learning Repository

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.