Select your cookie preferences

We use essential cookies and similar tools that are necessary to provide our site and services. We use performance cookies to collect anonymous statistics, so we can understand how customers use our site and make improvements. Essential cookies cannot be deactivated, but you can choose “Customize” or “Decline” to decline performance cookies.

If you agree, AWS and approved third parties will also use cookies to provide useful site features, remember your preferences, and display relevant content, including relevant advertising. To accept or decline all non-essential cookies, choose “Accept” or “Decline.” To make more detailed choices, choose “Customize.”
Sign in
Sign in
or
Create a new account
About
Categories
Delivery Methods
Solutions
Resources
 Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

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.

product logo

GPT-2 - Text generation

By:
Inmatura
1 AWS review
Generate text using the largest GPT-2 algorithm
  • This product has been removed and is no longer available to new customers.

Product Overview

This models provides text generation from an input based on the largest GPT-2 algorithm available with 1.5 billion parameters. It provides state of the art results in text generation It features a complete API that exposes multiple parameters to control the generated text. Simple pricing model where only pay for what you use with a simple metered pricing model. See docs, examples and more info at: https://docs.extrapolations.dev/models/gpt-2

Key Data

By
Inmatura
Categories
Generation-Text
Natural Language Processing
Text
Type
Model Package
Fulfillment Methods
Amazon SageMaker

Highlights

  • GPT-2 is a large transformer-based language model with 1.5 billion parameters that achieves state of the art text-generation

  • Multiple modes of operation and parameters to control the generated sequences makes it easy to generate text for in a variety of contexts

  • Only pay for what you use with a simple metered pricing model

Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us

Usage Information

Model input and output details

Input

Summary

Input of is a JSON object that includes the input text and the different modes and parameters that controls the text generated.

For example:

{
    "input": "This is the input of the algorithm",
    "max_length": 50,
    "mode": "sample-top-p",
    "top_p": 0.92,
    "top_k": 50,
    "temperature": 0.7,
    "num_beams": 5,
    "no_repeat_ngram_size": 2,
    "num_return_sequences": 3,
    "seed": -1
}

For more information see the docs at: https://docs.extrapolations.dev/models/gpt-2/api

Input MIME type
application/json
Sample input data
Expand all input descriptions
Field name
input
Description
Input text to be completed
Required
Yes
Data type
FreeText
Field name
max_length
Description
Maximun length of the text to be generated.
Required
No
Data type
Integer
Range
Default value
50
Field name
mode
Description
Controls the different modes to generate text. For more info see: https://docs.extrapolations.dev/models/gpt-2/api/
Required
No
Data type
Categorical
Default value
sample-top-p
Allowed values
sample-top-p, sample-top-k, sample, beam, greedy
Usage information

Output

Summary

The output of the API is a list of generated sequences based on the initial input. For example:

[
    'This is the input of the algorithm, and you can see that it has a few iterations (3, 4, 5, 6) and ends with...',
    'This is the input of the algorithm, which is a string (a list of letters) separated by a period ...',
    'This is the input of the algorithm. The values you enter should be numbers in the range ...'
]
Output MIME type
application/json
Sample output data
Expand all output descriptions
Field name
response
Description
List of generated sequences
Always returned
Yes
Data type
FreeText

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 More

Refund Policy

You may cancel your subscription at any time; However, we will not refund payments made by you under the agreement.

Customer Reviews

Farshad
How to perform batch inference in Sagemaker?
Jan 18, 2021Verified purchase review from AWS Marketplace
Hi Daniel,
I'm using the GPT-2 model shared by you. I want to get synthetic texts from multiple input texts, using
batch inference API of AWS Sagemaker. There is a github repo that contains a batch infer... Read more... Read more
View all

Reviews from AWS Marketplace

1 AWS review