Know a great resource on GPT-2? Send it to us at!

Tags: Transformers, GPT-1


Language Models are Unsupervised Multi-task Learners

  • OpenAI’s paper introducing GPT-2

Release Strategies and the Social Impacts of Language Models

  • A follow up paper to GPT-2 on it and related model’s potential social impact


GPT-2 Explained

  • A look at the GPT-2 paper by Henry AI Labs

GPT-2 Paper Walkthrough

  • By Yannic Kilcher


The Illustrated GPT-2

  • Detailed explanation of GPT-2 with visuals

GPT-2 - Generalized Language Models

  • A section on GPT-2 from a Lilian Weng blog post

Better Language Models and Their Implications, 6-Month Follow-Up, and GPT-2 Code Release

  • A series of 3 blog posts by OpenAI on GPT-2

Code Examples

OpenAI’s GPT-2 Code

  • Code of GPT-2 released by OpenAI

Karpathy’s minGPT

  • A pytorch implementation of a mini GPT for learners


  • A tensorflow recreation of Karpathy’s minGPT


Transformers - GPT-2 API

  • An api for state of the art Natural Language Processing tasks in pytorch and tensorflow

Paper for the api

Chatting Transformer

  • An API for generating text with GPT-2

Tagged Pages: GPT-3

Know a great resource on GPT-2? Send it to us at!