shumingma

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

dalle-mini

DALL·E Mini - Generate images from a text prompt

finetune-transformer-lm

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

infinibatch

Efficient, check-pointed data loading for deep learning with massive data sets.

Megatron-LM

shumingma.github.io

unilm

UniLM AI - Unified "Language" Model Pre-training across Tasks, Languages, and Modalities

vizseq

An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)