Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
SmartDescriptions Free trial
By:
Latest Version:
1.0.0
SmartDescriptions algorithm allows you to generate text from structured data
Product Overview
SmartDescriptions is a data-to-text solution that allows you to generate text from structured data. With the SmartDescriptions solution, you can automatically save time by generating thousands of comprehensible texts. Large companies whose business model is sale are constantly faced with the challenge of describing their hundreds of products and services. With this solution, you can create product descriptions at the push of a button. You can finetune the SmartDescriptions solution to generate texts according to your business domain. This algorithm was developed by adapting and finetuning a HuggingFace Model.
Key Data
Version
Type
Algorithm
Highlights
Natural Language Generation (NLG): Generate natural written text from structured data.
You can use SmartDescriptions to customize the generation of text from your own structured data. Provide a training dataset and create your own model for a specific business domain.
In case you do not have a dataset for training or you’re looking for pretrained models you can contact us directly (info@newtoms.com)
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Contact us to request contract pricing for this product.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Algorithm Training$0.50/hr
running on ml.g4dn.xlarge
Model Realtime Inference$0.50/inference
running on any instance
Model Batch Transform$0.50/hr
running on ml.m5.xlarge
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Algorithm Training$0.736/host/hr
running on ml.g4dn.xlarge
SageMaker Realtime Inference$0.23/host/hr
running on ml.m5.xlarge
SageMaker Batch Transform$0.23/host/hr
running on ml.m5.xlarge
About Free trial
Try this product for 5 days. There will be no software charges, but AWS infrastructure charges still apply. Free Trials will automatically convert to a paid subscription upon expiration.
Algorithm Training
For algorithm training in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Algorithm/hr | |
|---|---|---|
ml.m5.large | $0.50 | |
ml.m5.2xlarge | $0.50 | |
ml.g4dn.xlarge Vendor Recommended | $0.50 | |
ml.m5.xlarge | $0.50 | |
ml.g4dn.2xlarge | $0.50 |
Usage Information
Training
This algorithm requires a JSON line file, each line will contain an object with the attributes "data" and "response" in this respective order.
Channel specification
Fields marked with * are required
train
Input modes: File
Content types: application/json
Compression types: None
Hyperparameters
Fields marked with * are required
model_name_or_path
*model_name_or_path
Type: Categorical
Tunable: No
output_dir
*output_dir
Type: Categorical
Tunable: No
sagemaker_program
*sagemaker_program
Type: Categorical
Tunable: No
do_train
*sagemaker_program
Type: Categorical
Tunable: No
train_file
*/opt/ml/input/data/train/train_algorithm.json
Type: Categorical
Tunable: No
num_train_epochs
*Hyperparameter used to determine the amount of epochs
Type: Integer
Tunable: No
per_device_train_batch_size
*Hyperparameter used to determine the train batch size
Type: Integer
Tunable: No
per_device_eval_batch_size
*Hyperparameter used to determine the evaluation batch size
Type: Integer
Tunable: No
Model input and output details
Input
Summary
This algorithm requires a JSON line file, each line will contain an object with the attributes "inputs" and "parameters"
Input MIME type
application/json, application/jsonlinesSample input data
Output
Summary
The output of the algorithm is a comprehensive text generated from the stuctured data
Output MIME type
application/json, application/jsonlinesSample output data
Sample notebook
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
AWS Infrastructure
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.
Learn MoreRefund Policy
Contact us. EMAIL. info@newtoms.com TELEPHONE. +1-678-736-3022
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review