GPT-2
OpenAI published a description of GPT-2.
Why it matters
It showed how a large Transformer could generate coherent continuations from prompts.
OpenAI’s publication also discusses release risks and staged sharing.
Research · February 2019
OpenAI published a description of GPT-2.
It showed how a large Transformer could generate coherent continuations from prompts.
OpenAI’s publication also discusses release risks and staged sharing.
OpenAI · Published February 2019
The GPT-2 technical description identifies Transformer-based language modeling.
GPT-2The study measured models of the same architectural family.
The assistant rests on the GPT line of language models.
The direct predecessor of GPT-2, eight months later.
Improving Language Understanding by Generative Pre-TrainingThe same architecture, scaled up a hundredfold.
Language Models are Few-Shot LearnersThe company's first open weights since GPT-2 in 2019.
The law was passed five months before GPT-2 was described and is written about automated accounts, not language models; its disclosure duty also covers a bot running on such a model.