GPT-2
Also known as Generative Pre-trained Transformer 2, Generative Pretrained Transformer 2, GPT2
Generative Pre-trained Transformer 2 (GPT-2) is a large language model by OpenAI and the second in their foundational series of GPT models. GPT-2 was pre-trained on a dataset of 8 million web pages. It was partially released in February 2019, followed by full release of the 1.5-billion-parameter model on November 5, 2019.
Key facts
- Software.name
- Generative Pre-trained Transformer 2 (GPT-2)
- Software.screenshot
- File:GPT2-talks-about-GPT2.png
- Software.caption
- GPT-2 completion using the Hugging Face Write With Transformer website, prompted with text from this article (All highlighted text after the initial prompt is machine-generated from the first suggested completion, without further editing.)
- Software.author
- OpenAI
- Software.repo
- https://github.com/openai/gpt-2
- Software.replaces
- GPT-1
- Software.replaced_by
- GPT-3
- Software.license
- MIT
via Wikipedia infobox
Source code
Code and models from the paper "Language Models are Unsupervised Multitask Learners". You can read about GPT-2 and its staged release in our original blog post, 6 month follow-up post, and final post. Note that our original parameter counts were wrong due to an error (in our previous blog posts and paper). Thus you may have seen small referred to as 117M and medium referred to as 345M. Some caveats 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 our 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. Our models are often incoherent or inaccurate in subtle ways, which takes more than a quick read for a human to notice.
~15 min read
Article
11 sectionsContents
- Training
- Release
- Restrictions and partial release
- 774M release
- Full 1.5B release
- Small and Medium Releases
- Limitations
- Application and subsequent research
- Performance and evaluation
- See also
- References
Generative Pre-trained Transformer 2 (GPT-2) is a large language model by OpenAI and the second in their foundational series of GPT models. GPT-2 was pre-trained on a dataset of 8 million web pages. It was partially released in February 2019, followed by full release of the 1.5-billion-parameter model on November 5, 2019.
GPT-2 was created as a "direct scale-up" of GPT-1 with a ten-fold increase in both its parameter count and the size of its training dataset. It is a general-purpose learner and its ability to perform the various tasks was a consequence of its general ability to accurately predict the next item in a sequence, which enabled it to translate texts, answer questions about a topic from a text, summarize passages from a larger text, and generate text output on a level sometimes indistinguishable from that of humans; however, it could become repetitive or nonsensical when generating long passages. It was superseded by the GPT-3 and GPT-4 models, which are no longer open source.