nodd-repo/support-triage

support_triage (v2)

Route an incoming customer support message to the right queue.

A small classifier trained with nodd, exported as ONNX fp32 and int8 for browser and Node.js inference. This version uses a larger offline synthetic training dataset.

Label	Meaning
billing	Charges, refunds, invoices, plans, pricing, discounts and payment methods.
bug	Something in the product is broken, crashes, shows errors or behaves wrongly.
account	Login, passwords, 2FA, email or owner changes, access, security and account deletion.
how_to	A question about how to use something the product already does.
feature_request	Asks for something the product doesn't do yet, or suggests an improvement.

Evaluation

Metric	Value
Test macro F1, PyTorch	0.9178
Test macro F1, int8 ONNX	0.9389
int8 vs PyTorch label agreement	98.00%
int8 download	24.31 MB
Train / validation / test	5231 / 50 / 50
Temperature	1.248247
Confidence threshold	0.951806
Validation precision at threshold	97.62%
Test accuracy on covered inputs, PyTorch	93.48%
Test coverage, PyTorch	92.00%
Training seed	42

See baseline comparison, evaluation report, and browser parity results.

Data and limitations

Added 1,000 examples per label using deterministic offline templates, with generation seed 20260928. Labels were assigned by construction, not by an independent teacher. Template variants are correlated and do not represent independent scenarios. New rows are training-only; the original validation and test records were preserved. Exact duplicates and examples with embedding cosine similarity above 0.90 to either holdout were rejected.

All evaluation inputs are synthetic; real-world accuracy is unmeasured. More data did not consistently improve held-out quality: consult the comparison before replacing an earlier version. The 97% precision target selected on validation was not met on this version's covered PyTorch test subset. Quantization can change individual probabilities substantially, so label parity does not establish confidence equivalence. Prompt-injection detection, where applicable, is not a standalone security boundary.

Use

Download this version and serve it from your own origin:

hf download nodd-repo/support-triage --revision v2 --local-dir public/models/support_triage/v2
npm install @nodd/browser

import { nodd } from "@nodd/browser";
const model = await nodd.load("/models/support_triage/v2");
const decision = await model.decide("Your input text");
if (!model.isConfident(decision)) { /* escalate for review */ }
model.dispose();

For Node.js, use @nodd/node and the downloaded directory path. Requires nodd JavaScript packages >= 0.2.0.

Artifacts

• onnx/model_quantized.onnx, onnx/model.onnx: int8 and fp32 browser models.
• nodd.json, tokenizer files and config.json: browser runtime configuration.
• encoder/: original Transformers checkpoint, loadable with AutoModelForSequenceClassification.from_pretrained(local_path, subfolder="encoder").
• labeled.jsonl: exact training, validation and test records with split and provenance fields.
• synthetic_manifest.json: generation metadata and baseline fingerprint.
• model_card.json, reports and parity files: training, calibration and evaluation evidence.

Earlier releases remain available through their version tags. The generation script and cross-task results are in the source repository.