How Study Schedule Note Parser 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 Extract 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 organise a student's study note. Extract deadlines, times the student is busy, and study tasks exactly as written (keep days, dates and times in the student's words). Do not work out dates, count days or add hours; if the note does not say when something happens, leave it out of the deadlines and list it as an open question.
What it returns
- Deadlines and exams: Each exam or due date, written as 'what - when', using the note's wording.
- Times you are not free: Work shifts, practices or other commitments mentioned, with their days or times.
- Study tasks: Each study task mentioned (practice tests, chapters to read, flashcards), with any 'before' or 'by' condition.
- Missing details: Things the note leaves unclear, such as a task with no deadline.