* [The Illustrated GPT-2 (Visualizing Transformer Language Models) – Jay Alammar – Visualizing machine learning one concept at a time.](https://jalammar.github.io/illustrated-gpt2/) * [完全图解GPT-2：看完这篇就够了（一） - 知乎](https://zhuanlan.zhihu.com/p/79714797) * [完全图解GPT-2：看完这篇就够了（二） - 知乎](https://zhuanlan.zhihu.com/p/79872507) * [Fine-tune GPT2 for Text Generation Using Pytorch | Towards Data Science](https://towardsdatascience.com/fine-tuning-gpt2-for-text-generation-using-pytorch-2ee61a4f1ba7) * [itsuncheng/fine-tuning-GPT2: Codebase for the Medium Article on Fine-tuning GPT2 for Text Generation](https://github.com/itsuncheng/fine-tuning-GPT2) * [Beginner’s Guide to Retrain GPT-2 (117M) to Generate Custom Text Content | by Ng Wai Foong | AI Innovation | Medium](https://medium.com/ai-innovation/beginners-guide-to-retrain-gpt-2-117m-to-generate-custom-text-content-8bb5363d8b7f) * [nshepperd/gpt-2: Code for the paper "Language Models are Unsupervised Multitask Learners"](https://github.com/nshepperd/gpt-2) * [Fine-tune a non-English GPT-2 Model with Huggingface | by Philipp Schmid | Towards Data Science](https://towardsdatascience.com/fine-tune-a-non-english-gpt-2-model-with-huggingface-9acc2dc7635b) Code|Support Chinese|Framework|Remark -------|-----------------------|--------------|----------- [openai/gpt-2: Code for the paper "Language Models are Unsupervised Multitask Learners"](https://github.com/openai/gpt-2)|No|Tensorflow 1.x|Official (Open AI) one; [Better Language Models and Their Implications](https://openai.com/blog/better-language-models/) [minimaxir/gpt-2-simple: Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts](https://github.com/minimaxir/gpt-2-simple)|No|Tensorflow 1.x|[minimaxir/textgenrnn: Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.](https://github.com/minimaxir/textgenrnn); [OpenAI「假新闻」生成器GPT-2的最简Python实现 - 知乎](https://zhuanlan.zhihu.com/p/63185405) [yangjianxin1/GPT2-chitchat: GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)](https://github.com/yangjianxin1/GPT2-chitchat)|Yes|PyTorch|Very cool project based on Huggingface; [用于中文闲聊的GPT2模型：GPT2-chitchat - 知乎](https://zhuanlan.zhihu.com/p/96755231) [rish-16/gpt2client: ✍🏻 gpt2-client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models 🤖 📝](https://github.com/rish-16/gpt2client)|No|TensorFlow 1.x|[新加坡高中生开源轻量级GPT-2“客户端”：五行代码玩转GPT-2 - 知乎](https://zhuanlan.zhihu.com/p/77729450) [Morizeyao/GPT2-Chinese: Chinese version of GPT2 training code, using BERT tokenizer.](https://github.com/Morizeyao/GPT2-Chinese)|Yes|PyTorch|Based on Huggingface Huggingface > GPT2LMHeadModel * [OpenAI GPT2 — transformers 3.4.0 documentation](https://huggingface.co/transformers/model_doc/gpt2.html) * [Examples — transformers 2.0.0 documentation (About fine-tune)](https://huggingface.co/transformers/v2.0.0/examples.html#gpt-2-gpt-and-causal-language-modeling) * [Converting Tensorflow Checkpoints — transformers 3.4.0 documentation](https://huggingface.co/transformers/converting_tensorflow_models.html#openai-gpt-2) * [How to train a new language model from scratch using Transformers and Tokenizers](https://huggingface.co/blog/how-to-train) TODO: WWM?!
Huggingface
TODO: WWM?!