Zap v1: 20.7M-param web form & field classifier for autofill (bf16, MIT)

e4805d0 verified about 1 month ago

1.5 kB

// CPU latency benchmark: model-only time per form (extraction excluded), onnxruntime-node via transformers.js
import fs from "fs"; import path from "path"; import { createRequire } from "module";
const require = createRequire(import.meta.url);
const tf = require("@huggingface/transformers");
const { JSDOM, VirtualConsole } = require("jsdom");
const { zapExtract } = require("./zap-extract.js");
const { ZapModel } = require("./zap-infer.js");
const [modelDir, dir, dtype] = process.argv.slice(2);
tf.env.allowRemoteModels = false; tf.env.localModelPath = path.dirname(path.resolve(modelDir)) + "/";
const zap = await ZapModel.load(tf, path.basename(modelDir), { dtype: dtype || "fp32" });
const pages = JSON.parse(fs.readFileSync(path.join(dir, "py.json"), "utf8")).slice(0, 200);
const vc = new VirtualConsole(); const forms = []; let tx = 0;
for (const p of pages) { const d = new JSDOM(fs.readFileSync(path.join(dir, p.file), "utf8"), { url: p.url, virtualConsole: vc });
  const t = performance.now(); forms.push(...zapExtract(d.window.document, p.url)); tx += performance.now() - t; }
await zap.classify(forms.slice(0, 20)); // warmup
const t0 = performance.now(); const res = await zap.classify(forms); const dt = performance.now() - t0;
const nf = forms.reduce((a, f) => a + f.fields.length, 0);
console.log(JSON.stringify({ dtype: dtype || "fp32", forms: forms.length, fields: nf, ms_per_form: +(dt / forms.length).toFixed(2), extract_ms_per_form: +(tx / forms.length).toFixed(2) }));

	// CPU latency benchmark: model-only time per form (extraction excluded), onnxruntime-node via transformers.js
	import fs from "fs"; import path from "path"; import { createRequire } from "module";
	const require = createRequire(import.meta.url);
	const tf = require("@huggingface/transformers");
	const { JSDOM, VirtualConsole } = require("jsdom");
	const { zapExtract } = require("./zap-extract.js");
	const { ZapModel } = require("./zap-infer.js");
	const [modelDir, dir, dtype] = process.argv.slice(2);
	tf.env.allowRemoteModels = false; tf.env.localModelPath = path.dirname(path.resolve(modelDir)) + "/";
	const zap = await ZapModel.load(tf, path.basename(modelDir), { dtype: dtype \|\| "fp32" });
	const pages = JSON.parse(fs.readFileSync(path.join(dir, "py.json"), "utf8")).slice(0, 200);
	const vc = new VirtualConsole(); const forms = []; let tx = 0;
	for (const p of pages) { const d = new JSDOM(fs.readFileSync(path.join(dir, p.file), "utf8"), { url: p.url, virtualConsole: vc });
	const t = performance.now(); forms.push(...zapExtract(d.window.document, p.url)); tx += performance.now() - t; }
	await zap.classify(forms.slice(0, 20)); // warmup
	const t0 = performance.now(); const res = await zap.classify(forms); const dt = performance.now() - t0;
	const nf = forms.reduce((a, f) => a + f.fields.length, 0);
	console.log(JSON.stringify({ dtype: dtype \|\| "fp32", forms: forms.length, fields: nf, ms_per_form: +(dt / forms.length).toFixed(2), extract_ms_per_form: +(tx / forms.length).toFixed(2) }));