MOSS-Moon-003

Training compute

6.7×10²² FLOP

Parameters

16B

Published

Apr 19, 2023

MOSS-Moon-003 is an AI model developed by Fudan University (China), first published in April 2023. It works in the language domain, on tasks such as code generation.

Training it took an estimated 6.7×10²² FLOP of compute (estimation method: operation counting). The model has 16,000,000,000 parameters. It was trained on roughly 700B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of CodeGen-Mono 16.1B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Fudan University
Country of organization: China
Domain: Language
Task: Code generation
Training compute: 6.7×10²² FLOP
Compute estimation method: Operation counting
Parameters: 16,000,000,000
Dataset size: 700B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: CodeGen-Mono 16.1B
Epoch confidence: Confident