Skip to main content

High level interface for text applications using PyTroch RNN's.

Project description


GitHub license

GeNN (generative neural networks) is a high-level interface for text applications using PyTorch RNN's.


  1. Preprocessing:
    • Parsing txt, json, and csv files.
    • NLTK, regex and spacy tokenization support.
    • GloVe and fastText pretrained embeddings, with the ability to fine-tune for your data.
  2. Architectures and customization:
    • GPT-2 with small, medium, and large variants.
    • LSTM and GRU, with variable size.
    • Variable number of layers and batches.
    • Dropout.
  3. Text generation:
    • Random seed sampling from the n first tokens in all instances, or the most frequent token.
    • Top-K sampling for next token prediction with variable K.
    • Nucleus sampling for next token prediction with variable probability threshold.

Getting started

How to install

pip install genn


  • PyTorch 1.4.0
pip install torch==1.4.0
  • Pytorch Transformers
pip install pytorch_transformers
  • NumPy
pip install numpy
  • fastText
pip install fasttext

Use the package manager pip to install genn.


from genn import Preprocessing, LSTMGenerator, GPT2
#LSTM example
ds = Preprocessing("data.txt")
gen = LSTMGenerator(ds, nLayers = 2,
                        batchSize = 16,
                        embSize = 64,
                        lstmSize = 16,
                        epochs = 20)

#Train the model

# Generate 5 new documents

#GPT-2 example
gen = GPT2("data.txt",
 	    taskToken = "Movie:",
	    epochs = 7,
	    variant = "medium")
#Train the model

#Generate 10 new documents

For more examples on how to use Preprocessing, please refer to this file.

For more examples on how to use LSTMGenerator and GRUGenerator, please refer to this file.

For more examples on how to use GPT2, please refer to this file


Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.


Distributed under the MIT License. See LICENSE for more information.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for abdoTheBest, version 0.9.1
Filename, size File type Python version Upload date Hashes
Filename, size abdoTheBest-0.9.1-py3-none-any.whl (17.4 kB) File type Wheel Python version py3 Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page