nlp2go

Hosting nlp models in one line

Demo

demo website

Introduction

Once the model is trained, we want to verify our model as quickly as possible. nlp2go provides a CLI interface and Restful api that allows you to quickly deploy model to everyone.

Feature

There are many additional features :

• Support loading multiple models at a time.
• Provide input format checking.
• You can also load models in python code.
• Flexible handling of parameters so that parameter can be changed in each prediction.
• Support huggingface transformers’s model
• There are models in the Model Hub for you to try

Documentation

Learn more from the docs.

Quick Start

Installing via pip

pip install nlp2go

hosting single model

nlp2go --model model_path 

hosting multiple models

1. create a json file as below:

{
    "API1_PATH": {
      "model": "model1_path"
    },
    "API2_PATH": {
      "model": "model2_path"
    }
}

2. run

nlp2go --json json_file_path  

You can also try nlp2go in Google Colab:

Contributing

Thanks for your interest.There are many ways to contribute to this project. Get started here.

License

• License

Icons reference

Icons modify from Good Ware from www.flaticon.com
Icons modify from Freepik from www.flaticon.com