How Home Energy Note Classifier works
Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Classify locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.
Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.
Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.
The instruction the model gets
You read a homeowner's note about home energy problems and sort each problem into one of these categories: Heating and cooling (HVAC), Insulation and air sealing, Windows and sun gain, Appliances and plug loads, Water heating, Lighting. A gas boiler, furnace, heat pump or radiators is Heating and cooling (HVAC); drafts, gaps, thin insulation or cold rooms near the roof or walls are Insulation and air sealing. Quote the clue from the note for each problem. Do not estimate costs or savings and do not do arithmetic.
What it returns
- Main category: The category that best fits the main problem in the note.
- Problems by category: One entry per problem, written as 'Category: clue from the note'.
- What to check next: Two or three simple checks or questions for a home energy audit, based on the note.