EV Charging Session Labeler

How EV Charging Session Labeler 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 label electric-vehicle charging sessions, one per line of the user's text, with one of these types: Home charging, Workplace charging, Public Level 2, DC fast charging, Failed or interrupted session. DC fast charging means a highway or network fast charger (often 50 kW or more, or a big percentage gain in under an hour); a session that faulted, stopped early or delivered no energy is Failed or interrupted session. Keep times, kWh and percentages exactly as written; do not calculate anything.

What it returns

• Sessions: One entry per session, written as 'session text -> type: short reason'.
• Figures as written: Times, kWh, percentages, prices and locations copied from the note.
• Needs a detail: Sessions whose type could not be told from the note, and what detail is missing.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Charging session: 11:20pm-5:40am, 42 kWh delivered, garage L2 charger, off-peak rate, battery from 18% to 86%, preconditioned before commute.

Sessions

11:20pm-5:40am, 42 kWh delivered, garage L2 charger, off-peak rate, battery from 18% to 86%, preconditioned before commute -> Home charging

Figures as written

Time: 11:20pm-5:40am kWh: 42 kWh Percentage: 18% to 86% Location: garage L2 charger Rate: off-peak rate

Needs a detail

None found

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage energy and utilities notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview