🦄 Building a State-of-the-Art Conversational AI with Transfer Learning

The present repo forked the code accompanying the blog post 🦄 How to build a State-of-the-Art Conversational AI with Transfer Learning.

I added a Flask app to generate a Conversational AI prototype with the help of Javascript and Firebase database. Currently the code requires a GPU and supports only the OpenAIGPT language model.

Installation

To install and use the training and inference scripts please clone the repo and install the requirements:

Pretrained model

We make a pretrained and fine-tuned model available on our S3 here. The easiest way to download and use this model is just to run the interact.py script to talk with the model. Without any argument, this script will automatically download and cache our model.

Citation

@article{DBLP:journals/corr/abs-1901-08149,
  author    = {Thomas Wolf and
               Victor Sanh and
               Julien Chaumond and
               Clement Delangue},
  title     = {TransferTransfo: {A} Transfer Learning Approach for Neural Network
               Based Conversational Agents},
  journal   = {CoRR},
  volume    = {abs/1901.08149},
  year      = {2019},
  url       = {http://arxiv.org/abs/1901.08149},
  archivePrefix = {arXiv},
  eprint    = {1901.08149},
  timestamp = {Sat, 02 Feb 2019 16:56:00 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1901-08149},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

ToDo

Add code to plug a GPT2 pretrained model and to fine tune one as well.