Conditional Maximum Entropy Model (Gigaworld)

Training compute

10¹⁸ FLOP

Parameters

1M

Published

Jul 1, 2009

Conditional Maximum Entropy Model (Gigaworld) is an AI model developed by Google (United States), first published in July 2009. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 10¹⁸ FLOP of compute. The model has 1,000,000 parameters. It was trained on roughly 1B datapoints.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: Google
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 10¹⁸ FLOP
Parameters: 1,000,000
Dataset size: 1B
Chip-hours: 18.6K
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Speculative