GPT-2 (355M)

Training compute

2.3×10²¹ FLOP

Parameters

355M

Published

Feb 14, 2019

GPT-2 (355M) is an AI model developed by OpenAI (United States), first published in February 2019. It works in the language domain, on tasks such as language modeling/generation. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 2.3×10²¹ FLOP of compute. The model has 355,000,000 parameters. It was trained on roughly 10.7B datapoints. The compute alone is estimated at $9K in 2023 dollars.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 26,463 citations. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Language
Task: Language modeling/generation
Training compute: 2.3×10²¹ FLOP
Parameters: 355,000,000
Dataset size: 10.7B
Training cost (2023 USD): $9K
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 26,463
Epoch confidence: Speculative