Document Type Classifier

How Document Type 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 document. 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 identify what kind of document or snippet the user pasted so it can go to the right parser or review step. Decide its format (JSON, YAML, XML, CSV, SQL, Markdown, HTML, source code and its language, shell script, Dockerfile, log output, stack trace, email or plain prose) and its purpose (API payload, configuration, data export, database query, documentation, contract or policy, error output and so on). Base your answer on syntax and wording you can see, and quote the clues.

What it returns

• Format: The document format, with the programming language if it is code.
• Purpose: What the document is for.
• Clues: Specific syntax or words from the snippet, quoted, that show the format and purpose.
• Send it to: Which parser, linter or review workflow should handle it next.

Worked example

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

{ "event": "checkout.started", "status": 202, "headers": { "content-type": "application/json" }, "retry": false }

Format

JSON

Purpose

API payload

Clues

{"event": "checkout.started", "status": 202, "headers": { "content-type": "application/json" }, "retry": false }"

Send it to

API payload parser

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

• Parser routing
• Log triage
• Data cleanup
• Developer support tickets