Sold by: AUM Labs
Deployed on AWS
Free Trial
Sentence Embedding based on the RoBERTa Model https://huggingface.co/FacebookAI/roberta-base for running on GPUs
Overview
RoBERTa base model: Pretrained model on the English language using a masked language modeling (MLM) objective. It was introduced in this paper (https://arxiv.org/abs/1907.11692 ) and first released in this repository (https://github.com/facebookresearch/fairseq/tree/main/examples/roberta ). This Service sets up an endpoint on AWS Sagemaker that returns text embeddings based on the RoBERTa model. Use this service if you plan to run it on GPU.
For running it on CPU use https://aws.amazon.com/marketplace/pp/prodview-nvrw726ubwj26
Keywords: Embedding, RoBERTa, BERT, Retrieval augmented generation, facebook, classifier, text, NLP
Highlights
- RoBERTa Model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. If you have a dataset of labeled sentences for instance, you can train a standard classifier using the embedding produced by the RoBERTa model as inputs.
- RoBERTa (Robustly Optimized BERT Approach) is a transformer-based language model developed by Facebook AI as an improvement over the BERT (Bidirectional Encoder Representations from Transformers) model. Like BERT, it is designed for natural language processing (NLP) tasks such as text classification, question answering, sentiment analysis, building RAG solutions, and more. However, RoBERTa incorporates several optimizations to enhance its performance and scalability.
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
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.g5.2xlarge Inference (Batch) Recommended | Model inference on the ml.g5.2xlarge instance type, batch mode | $0.30 |
ml.g5.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.2xlarge instance type, real-time mode | $0.30 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $0.30 |
ml.g5.8xlarge Inference (Batch) | Model inference on the ml.g5.8xlarge instance type, batch mode | $0.30 |
ml.g5.12xlarge Inference (Batch) | Model inference on the ml.g5.12xlarge instance type, batch mode | $0.30 |
ml.g5.4xlarge Inference (Batch) | Model inference on the ml.g5.4xlarge instance type, batch mode | $0.30 |
ml.g5.48xlarge Inference (Batch) | Model inference on the ml.g5.48xlarge instance type, batch mode | $0.30 |
ml.g5.16xlarge Inference (Batch) | Model inference on the ml.g5.16xlarge instance type, batch mode | $0.30 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $0.30 |
ml.g6.16xlarge Inference (Real-Time) | Model inference on the ml.g6.16xlarge instance type, real-time mode | $0.30 |
Dimensions summary
You pay by the hour based on the GPU instance you run, with no per-token charges. Pricing splits into two modes. Batch mode runs on ml.g5 instances in eight sizes, from xlarge up to 48xlarge. Real-time mode covers ml.g5 and ml.g6 instances across similar size ranges, plus larger ml.p4d.24xlarge and ml.p5.48xlarge options. Within each mode, cost scales with instance size: bigger instances carry more GPU and memory capacity. You choose the mode that fits your workload, then the instance size that matches your throughput needs.
Top-of-mind questions for buyers
One HostHrs unit is one hour of the GPU instance running the model. You pay for each hour the instance stays active. The rate depends on the instance type you pick. Charges apply per running host-hour, not per token or per query processed.
Software charges meter running time only. When the instance is fully stopped, no HostHrs accrue. Underlying AWS infrastructure fees, such as storage, may still apply while resources exist. To stop software charges, shut the instance down.
Both modes bill by the hour on GPU instances. Batch mode processes grouped inputs together and runs on ml.g5 instances. Real-time mode returns results on demand and runs on ml.g5, ml.g6, ml.p4d, or ml.p5 instances. You pick the mode matching your workload, then the instance size.
aumlabs.ai
Helpful?
Vendor refund policy
Thank you for purchasing RoBERTa Embedding API on AWS Marketplace. We strive to ensure customer satisfaction with our services. If you have issues accessing the service contact us at support@aumlabs.ai
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
Additional details
Inputs
- Summary
This model can analyze text passed as json or json text files stored in Amazon S3 bucket.
- Limitations for input type
- Maximum payload size for endpoint invocation is 5MB while the maximum payload size for batch inference is 100 MB.
{
"sentences": [
"Hello, how are you doing?",
"I am doing great, how about you?"
]
}
https://github.com/aumlabs/aws-marketplace-listing/blob/main/sagemaker/roberta/data/input/batch/input.jsonl
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
sentences | An array of English text | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
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 Extractive Question Answering model from PyTorch Hub
This is a Sentence Pair Classification model built upon a Text Embedding model from Hugging Face
This is a Extractive Question Answering model from PyTorch Hub
This is a Sentence Pair Classification model built upon a Text Embedding model from Hugging Face
This is a Sentence Pair Classification model built upon a Text Embedding model from PyTorch Hub
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.