Sold by: Waltsoft Inc.
Deployed on AWS
sshleifer/distilbart-cnn-12-6 on SageMaker. ROUGE-2 21.26 on CNN/DailyMail. Summarize tickets, call transcripts, and documents in your own VPC -- no LLM token billing, flat $0.10/hr.
Overview
sshleifer/distilbart-cnn-12-6 is a distilled BART model fine-tuned for abstractive summarization on CNN/DailyMail, achieving ROUGE-2 21.26 and ROUGE-L ~30.6. It runs approximately 2x faster than the full bart-large-cnn while retaining comparable summarization quality, making it the practical choice for CPU-based production deployments.
Deploy as a SageMaker batch transform job for offline summarization of document corpora, or as a real-time endpoint for on-demand summarization. At 2-6 seconds per article on ml.m5.xlarge (depending on input length), it is well suited to asynchronous workflows -- summarize customer support transcripts overnight, generate document abstracts during ingestion, or condense meeting notes in near-real-time.
All processing happens in your AWS VPC. Unlike generative LLM summarization, there are no per-token charges -- you pay a flat $0.10/hr regardless of document volume.
Primary use cases: customer support call transcript summarization, legal and compliance document abstraction, news and research article digests, meeting notes condensation, and any pipeline that needs consistent abstractive summaries at scale without LLM token billing.
Highlights
- ROUGE-2 21.26 on CNN/DailyMail -- production summarization quality at 2x the speed of BART-large-cnn on the same CPU instance
- No LLM token billing -- flat $0.10/hr regardless of document volume, ideal for overnight batch summarization of large corpora
- Runs in your AWS VPC -- no document content leaves your account, compatible with SageMaker batch transform for large-scale offline jobs
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 |
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
sshleifer/distilbart-cnn-12-6 on SageMaker. ROUGE-2 21.26 on CNN/DailyMail. Summarize tickets, call transcripts, and documents in your own VPC -- no LLM token billing, flat $0.10/hr.
- 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
This is a Text Summarization model built upon a Transformer model from Hugging Face
This is a Text Summarization model built upon a Transformer model from Hugging Face
deepset/roberta-base-squad2 on SageMaker. F1 82.9 on SQuAD 2.0. Extracts literal text spans as answers -- structurally incapable of hallucination. $0.08/hr, all inference in your VPC.
1M+ monthly downloads. DistilBERT fine-tuned on CoNLL-03 for PER, ORG, LOC, MISC extraction. 40% faster than BERT-base NER at 90% of the accuracy.
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.