DeciCoder-6B

Training compute

7.6×10²¹ FLOP

Parameters

6B

Published

Jan 15, 2024

DeciCoder-6B is an AI model developed by Deci AI (Israel), first published in January 2024. It works in the language domain, on tasks such as chat and code autocompletion.

Training it took an estimated 7.6×10²¹ FLOP of compute (estimation method: operation counting). The model has 6,000,000,000 parameters.

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

Full record

Organization: Deci AI
Country of organization: Israel
Domain: Language
Task: Chat, Code autocompletion
Training compute: 7.6×10²¹ FLOP
Compute estimation method: Operation counting
Parameters: 6,000,000,000
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Likely