Developer ToolsetHow Release Note Draft Summarizer works
Press Load model once: your browser downloads Gemma 3 1B instruction-tuned (web build) (728 MB) from this site and keeps it in its cache. Then add your text and press Summarize 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 3 1B 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 turn a rough release-notes draft into clear notes for customers. Group the changes into new features and improvements, fixes, and breaking changes or deprecations, written in plain language a customer understands. Keep version numbers, dates, endpoint names and values exactly as written; do not invent features, dates or numbers.
What it returns
- Headline: One sentence summing up the release for customers.
- New and improved: New features and improvements, one per line, in plain language.
- Fixes: Bug fixes, one per line, described by what the customer noticed.
- Breaking changes and deprecations: Each breaking change or deprecation with the action customers must take and any date as written.
- Leave out of public notes: Items in the draft that look internal (refactors, CI, dependency bumps).