GPT

tags

Transformers, NLP

paper

(Radford et al. 2018)

Succesors

The GPT architecture was improved upon and extended into GPT-2 and GPT-3. The original “GPT-1” was quickly abandoned in favor of its successor, but GPT is still used to refer to this family of models.

Parameter count

117M

Bibliography

1. Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever. 2018. "Improving Language Understanding by Generative Pre-training". OpenAI.