OpenCALM

Training compute

9×10¹⁹ FLOP

Parameters

7B

Published

May 15, 2023

OpenCALM is an AI model developed by CyberAgent (Japan), first published in May 2023. It works in the language domain, on tasks such as chat.

Training it took an estimated 9×10¹⁹ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 2.1B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: CyberAgent
Country of organization: Japan
Domain: Language
Task: Chat
Training compute: 9×10¹⁹ FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Dataset size: 2.1B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Speculative