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. . . "Improving Language Understanding by Generative Pre-training". OpenAI.

Comments


← Back to Notes