Status: Public fork of the official GPT2 repository (archived).
Code and models from the paper "Language Models are Unsupervised Multitask Learners".
You can read about GPT-2 and its staged release in OpenAI's original blog post, 6 month follow-up post, and final post.
They have also released a dataset for researchers to study their behaviors.
* Note that their original parameter counts were wrong due to an error (in their previous blog posts and paper). Thus you may have seen small referred to as 117M and medium referred to as 345M.
This repository is meant to be a starting point for researchers and engineers to experiment with GPT-2.
For basic information, see the model card.
- GPT-2 models' robustness and worst case behaviors are not well-understood. As with any machine-learned model, carefully evaluate GPT-2 for your use case, especially if used without fine-tuning or in safety-critical applications where reliability is important.
- The dataset their GPT-2 models were trained on contains many texts with biases and factual inaccuracies, and thus GPT-2 models are likely to be biased and inaccurate as well.
- To avoid having samples mistaken as human-written, we recommend clearly labeling samples as synthetic before wide dissemination. Their models are often incoherent or inaccurate in subtle ways, which takes more than a quick read for a human to notice.
See DEVELOPERS.md