News Text Generator

Get this modelTry the API

Overview

This model generates English-language text similar to the text in the One Billion Word Benchmark Dataset. The input to the model is a simple text file, and the output is a string containing the words that are predicted to follow the input text. The model has a vocabulary of approximately 800,000 words.

Model Metadata

Domain Application Industry Framework Training Data Input Data Format
Text Language Modeling General TensorFlow One Billion Word Benchmark Dataset Text

References

Licenses

Component License Link
Model GitHub Repository Apache 2.0 LICENSE
Model weights Apache 2.0 TensorFlow Models Repository LICENSE
Model Code (3rd party) Apache 2.0 TensorFlow Models Repository LICENSE

Options available for deploying this model

  • Deploy from Dockerhub:

    docker run -it -p 5000:5000 codait/max-news-text-generator
    
  • Deploy on Red Hat OpenShift:

    Follow the instructions for the OpenShift web console or the OpenShift Container Platform CLI in this tutorial and specify codait/max-news-text-generator as the image name.

  • Deploy on Kuberneters:

    kubectl apply -f https://raw.githubusercontent.com/IBM/MAX-News-Text-Generator/master/max-news-text-generator.yaml
    
  • Locally: follow the instructions in the model README on GitHub

Example Usage

Once deployed, you can test the model from the command line. For example:

curl -F "text=@data/sample1.txt" -XPOST http://localhost:5000/model/predict

You should see a JSON response like that below:

{"status": "ok", "pred_txt": [{"pred_txt": "This is a test case .. but this is at least an investigation into the types of accidents they are involved  . </S> "}]}