cua-s1.js weights

Browser-ready ONNX exports of Cua's cua-s1 form-filling decision models, for @ai-ecoverse/cua-s1.js and onnxruntime-web. The model, its training data and the planning rules are Cua's work (MIT); this repo only holds the converted checkpoint.

import * as ort from "onnxruntime-web/wasm";
import { loadCuaS1, extractEntities } from "@ai-ecoverse/cua-s1.js";

const model = await loadCuaS1("https://huggingface.co/ai-ecoverse/cua-s1.js/resolve/main/cua-s1-forms", { ort });
const plan = await model.plan("Northwind Clinic - New Patient Registration",
  [{ role: "Edit", label: "Phone number", value: "", token: "phone" }],
  extractEntities("Tel: (503) 555-0142\nWork phone: (503) 555-0110"));

Contents

Folder	Source checkpoint	ONNX	Max |Δp| vs PyTorch
cua-s1-forms	cua-ai/cua-s1-forms @ f54adbf	3.3 MB	3.2e-06 over 1048 decisions

Each folder has a manifest.json naming its source commit, the ONNX graph's SHA-256 (checked by the loader) and the parity measured at export time. The graph and Cua's original JSON sidecar (checkpoint.json: architecture, tensor signature, training metadata) live under r-<commit>/, so publishing a new checkpoint never changes a file an older manifest points at.

Conversion

The checkpoint is loaded with cua_s1.model.load_checkpoint, which validates the SHA-256 tensor signature. It is exported unmodified with the torch.export-based ONNX exporter (opset 18, dynamic batch, context, option and option-token axes). It takes the byte tensors cua_s1's ByteCollator produces and returns per-option logits and probabilities. onnxruntime matches PyTorch to within the max |Δp| in the table, on 1,048 decisions from Cua's own synthetic episode generator, with no argmax flips.

cua-s1 is a research checkpoint trained on synthetic forms. Read Cua's model card and SECURITY.md before relying on it.