Deliver the ready-to-train data to your NLP model.

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

Scrap real time posts from twitter through the streaming api

Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)

Implements the paper " Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models" by Serban et al (currently on the MovieTriples dataset)

Pytorch implementation of Hierarchical Encoder Decoder Sequence to Sequence Model