RNTN

Training compute

1.4×10¹⁶ FLOP

Published

Oct 1, 2013

RNTN is an AI model developed by Stanford University (United States), first published in October 2013. It works in the language domain, on tasks such as sentiment classification.

Training it took an estimated 1.4×10¹⁶ FLOP of compute. It was trained on roughly 155.1K datapoints.

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

Full record

Organization: Stanford University
Country of organization: United States
Domain: Language
Task: Sentiment classification
Training compute: 1.4×10¹⁶ FLOP
Dataset size: 155.1K
Training time: 5 h
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Likely