Sold by: Sigmodata
Deployed on AWS
Free Trial
SageMaker model package for classifying the formality of English text
Overview
Image
Python predict
Image
POST /invocations
This SageMaker model package provides a REST API to classify English text as formal or informal, with a confidence score.
Use it to route or adapt content by register: enforcing a professional tone in business communications, filtering training data for style, or powering writing assistants.
The API accepts input as JSON or CSV and supports real-time endpoints and batch transform.
We welcome your feedback at aws-support@sigmodata.com
Model and training data The model is a ModernBERT-base (answerdotai/ModernBERT-base) text classifier fine-tuned with PyTorch and Hugging Face Transformers on the public osyvokon/pavlick-formality-scores dataset. It runs in network isolation on SageMaker, so no data leaves your account.
Known limitations
- English only. Other languages are not supported.
- The model was fine-tuned on inputs up to 512 tokens. Longer text is accepted, but accuracy is only characterized to that length; split long documents into passages before sending.
- Binary output (formal or informal) derived from human formality ratings, which are subjective near the middle of the scale.
Measured performance
- Accuracy 84.0 percent, macro-F1 0.838, measured on 2,254 held-out examples from pavlick-formality-scores. The split is seeded (70/20/10, seed 42) and was not used in training.
- Real-time endpoint on ml.m5.large: 249 ms median per request (265 ms p95).
- Throughput on the same instance: about 24 texts per second at a batch size of 32.
Highlights
- Sort English text into formal vs informal for tone routing, training-data filters, and writing aids
- Register/style classification - not sentiment or toxicity relabeled
- JSON or CSV with a confidence score; SageMaker real-time or batch
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.10 |
ml.m5.large Inference (Real-Time) Recommended | Model inference on the ml.m5.large instance type, real-time mode | $0.10 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $0.10 |
ml.c5.2xlarge Inference (Real-Time) | Model inference on the ml.c5.2xlarge instance type, real-time mode | $0.10 |
ml.c5.xlarge Inference (Batch) | Model inference on the ml.c5.xlarge instance type, batch mode | $0.10 |
ml.c5.xlarge Inference (Real-Time) | Model inference on the ml.c5.xlarge instance type, real-time mode | $0.10 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.10 |
ml.m5.2xlarge Inference (Real-Time) | Model inference on the ml.m5.2xlarge instance type, real-time mode | $0.10 |
ml.m5.xlarge Inference (Batch) | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
ml.m5.xlarge Inference (Real-Time) | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
Dimensions summary
You pay by the hour for the instance that runs the model, billed per host-hour. Pricing splits along two choices. First, pick an instance size across the ml.m5 and ml.c5 families, from ml.m5.large up to ml.c5.2xlarge, matching compute to your workload. Second, pick a mode: real-time for live endpoint requests, or batch for processing datasets in bulk. Each size-and-mode pairing is priced separately, so larger or compute-optimized instances cost more per hour. You choose one combination and pay only for the hours it runs.
Top-of-mind questions for buyers
One host-hour is one hour of a running instance that hosts the model. A real-time endpoint accrues charges the whole time it stays up, even between requests. Charges stop when you delete the endpoint. Batch jobs bill only for the hours the job runs.
Real-time mode runs a live endpoint that stays on to answer requests, so you pay for uptime whether or not text is flowing. Batch mode processes a dataset in one job and bills only for that job's duration. Real-time suits steady live traffic; batch suits bulk one-time processing.
No. You pay per host-hour of the instance, not per text or per request. Cost depends on the instance size you pick and how long it runs. Sending more text within the same running hours does not add a separate charge, though heavier volume may require a larger instance.
www.sigmodata.com
Helpful?
Vendor refund policy
No refunds offered but you may cancel at any time
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Important: security update. The inference container is rebuilt on Amazon Linux 2023, replacing a Debian base that carried HIGH and CRITICAL CVEs with no fixed version available upstream.
- The model itself is unchanged. This version is exported from the same fine-tuned checkpoint as version 1.
- Request and response formats are unchanged: JSON or CSV in, label plus confidence out.
Additional details
Inputs
- Summary
A JSON object with a "texts" array of strings to classify (or a CSV file, one text per line, for batch transform).
- Input MIME type
- application/json, text/csv
{"texts": ["yo wanna grab some food later?"]}
yo wanna grab some food later?
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
texts | List of text strings to classify | - | Yes |
Resources
Vendor resources
Support
Vendor support
Support contact: Email: support@sigmodata.com
Support description: contact: support@sigmodata.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
SageMaker model package for classifying customer banking queries into 77 intents
SageMaker model package for content safety and moderation classification
PaperScorer is a full service smart bubble scanning platform that empowers teachers to quickly and easily create bubble sheets, scan bubble sheets and review the data.
SageMaker model package for classifying news text into topics
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.