ricsinaruto/Seq2seqChatbots
A tensor2tensor wrapper for training and interacting with neural chatbot models using seq2seq and transformer architectures.

Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
This repository provides a flexible wrapper around TensorFlow’s tensor2tensor library to train, interact with, and generate data for neural chatbot systems. It integrates multiple dialogue datasets and supports any model or hyperparameter configuration available in tensor2tensor. The project includes a base class for dialog problems that can be easily extended for custom chatbot research and experimentation.