Sold by: Protopia AI, Inc.
Deployed on AWS
Llama-3.1-8B-Instruct with Stained Glass Transform Support, enabled via prompt-embeds support in vLLM.
Overview
Protopia AI's Stained Glass Transform (SGT) is a groundbreaking solution for organizations looking to leverage sensitive data in AI applications with robust security and flexibility. SGT transforms data into unintelligible forms, safeguarding against breaches and minimizing exposure risks without sacrificing fidelity. By enabling full data richness, SGT boosts value derived from AI models. With its low compute overhead, SGT operates efficiently on commodity hardware, freeing up powerful GPUs for critical tasks and offering greater flexibility across on-prem, multi-tenant, and edge environments. SGT's transformation process is fast, with minimal latency, integrating seamlessly into existing AI pipelines to maximize performance and throughput. For custom quotes and offers, please reach out at contact@protopia.ai
Highlights
- Unlock AI Data Potential Securely Access sensitive data without compromising security, enhancing AI model accuracy with high-quality inputs.
- Strengthen AI Security Convert data into unintelligible forms to eliminate exposure risks throughout AI pipelines.
- Stock Llama-3.1-8B-Instruct weights; the model you already know, now with support for protected prompts.
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
This product is available free of charge. Free 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.
Dimensions summary
This listing is free, so you pay only for the AWS compute you run. Pricing is organized by two choices. First, you pick an inference mode: batch, which processes grouped requests, or real-time, which serves live requests. Second, you pick an instance type from eight sizes, spanning CPU-based m5 instances and GPU-based p3, g4dn, and g5 instances. Every option bills per host hour (HostHrs), so cost scales with how long each instance runs. Larger or GPU-backed instances carry higher hourly rates. You match the mode and instance to your workload's speed and hardware needs.
Top-of-mind questions for buyers
One host hour is one running instance of the size you chose, billed for each hour it stays active. The count depends on how many instances run and for how long. Stopped instances stop accruing software charges, though underlying AWS resources like storage may still bill separately.
Batch mode processes grouped requests together, so an instance runs while it works through the queue. Real-time mode serves live requests, so the instance stays up to respond on demand. Both bill per host hour, so your choice affects how long instances run and accrue charges.
CPU-based m5 instances suit lighter workloads. GPU-based p3, g4dn, and g5 instances handle model inference that benefits from GPU acceleration. Stained Glass Transform runs on either CPUs or GPUs, so you pick the instance that matches your speed and hardware needs. Each size bills per host hour.
protopia.ai+1
Helpful?
Vendor refund policy
This package is provided free of charge, and no refunds will be provided.
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
Update manifest to include weights.
Additional details
Inputs
- Summary
Body is fully compatible with OpenAI Chat Completions and Completions request bodies. Note that only Completions-style requests are compatible with prompt embeddings, using vLLM's prompt_embeds key in the JSON body.
- Input MIME type
- application/json, application/jsonlines
{
"messages": [
{"role": "user", "content": "Why is the greenland shark the best shark?"},
],
"max_tokens": 150
}
{"messages": [{"role": "user", "content": "Why is the greenland shark the best shark?"},],"max_tokens": 150},
{"messages": [{"role": "user", "content": "Why is the greenland shark the best shark?"},],"max_tokens": 150},
{"messages": [{"role": "user", "content": "Why is the greenland shark the best shark?"},],"max_tokens": 150}
Resources
Vendor resources
Support
Vendor support
Please contact us for further support at support@protopia.ai
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
Available as a NIM, Llama 3.1 8B-Instruct is an 8B-parameter LLM pretrained, instruction tuned model optimized for multilingual dialogue.
Efficient, fast, and reliable generative AI inference solution of Llama 3.1 8B Instruct Int8 model
Available as a NIM, Llama 3.1 70B-Instruct is a 70B-parameter LLM pretrained, instruction tuned model optimized for multilingual dialogue.
![Stained Glass Transform for Llama-3.1-8B-Instruct [Private Offers Only]](https://d7umqicpi7263.cloudfront.net/img/product/d5b1f447-d4ef-49d8-9d72-8e4a9555961f.com/e7f58fd255573c62cbb35a11559140a0)
Stained Glass Transform (SGT) by Protopia AI allows organizations to securely unlock high-value data for AI applications without compromising privacy. With lightweight, high-speed transformations, SGT strengthens data security, and expands compute options across diverse environments, while retaining model accuracy.
This SGT is specifically to be used with Llama-3.1-8B-Instruct
Please reach out to us at contact@protopia.ai for customized pricing before making a purchase.
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.