Persimmon-8B

Training compute

4.1×10²² FLOP

Parameters

9.3B

Published

Sep 7, 2023

Persimmon-8B is an AI model developed by Adept (United States), first published in September 2023. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 4.1×10²² FLOP of compute (estimation method: operation counting). The model has 9,300,000,000 parameters. It was trained on roughly 737B datapoints.

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

Full record

Organization: Adept
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 4.1×10²² FLOP
Compute estimation method: Operation counting
Parameters: 9,300,000,000
Dataset size: 737B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident