Sold by: Waltsoft Inc.
Deployed on AWS
6M monthly downloads. 71MB zero-shot text classifier - assign any label without training data. CPU-optimized, Apache-2.0.
Overview
MiniLM NLI Zero-Shot Classifier enables label-free text classification using natural language inference. At 71MB, it runs on CPU with sub-100ms latency and handles any set of candidate labels without fine-tuning. Built on cross-encoder/nli-MiniLM2-L6-H768 from sentence-transformers, it achieves strong zero-shot accuracy on topic classification, intent detection, and content moderation tasks. Apache-2.0 licensed, fully commercial-safe.
Highlights
- 71MB CPU model - zero-shot classify any text without training data
- 6M monthly downloads - proven production NLI reliability
- Apache-2.0 - fully commercial-safe for any use case
Details
Sold by
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
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.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
Dimensions summary
You pay by the hour for model inference, billed per host hour on the ml.m5.xlarge instance type. Two options run on the same instance but differ by processing mode. The real-time option handles live, on-demand classification requests. The batch option processes grouped inputs together in scheduled jobs. Both scale with how many hours you run the instance, so your cost grows with usage time rather than a fixed subscription. Pick the mode that matches your workload; there are no tiers or commitments beyond hourly usage.
Top-of-mind questions for buyers
You run on the ml.m5.xlarge instance type, a CPU-based SageMaker instance. This model is built for CPU classification, so no GPU is required. You are billed per host hour the instance runs, regardless of how many requests it processes during that hour.
Charges accrue per host hour while the SageMaker instance runs. A stopped instance stops software metering. However, AWS may still bill underlying infrastructure or storage fees separately. The software charge here meters running host time only, not the number of classification requests.
Both meter the same per-host-hour rate on the same instance type. Real-time keeps the instance running to answer live requests, so it accrues hours continuously. Batch runs scheduled jobs, so it accrues hours only during those job windows. Choose real-time for on-demand needs, batch for grouped inputs.
waltsoft.net
Helpful?
Vendor refund policy
No refunds.
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
Initial release
Additional details
Inputs
- Summary
6M monthly downloads. 71MB zero-shot text classifier - assign any label without training data. CPU-optimized, Apache-2.0.
- Input MIME type
- application/json
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
Support
Vendor support
Contact support@waltsoft.net for deployment assistance.
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
A lightweight legal reranking and zero-shot classification/NLI model.
facebook/bart-large-mnli on SageMaker. MNLI accuracy 89.9. Classify any text into any custom category set with zero training data -- tickets, contracts, documents. $0.10/hr flat.
2.9M monthly downloads. Deeper 12-layer cross-encoder reranker for higher-accuracy RAG. Optimal precision-throughput balance for enterprise search.
~73M monthly downloads. The most deployed open reranker. Re-scores top-K retrieval results for precision RAG on CPU in ~10ms per query.
A state-of-the-art legal reranking and zero-shot classification/NLI model.
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.