gte-modernbert

Training compute

3.7×10²¹ FLOP

Parameters

149M

Published

Jan 22, 2025

gte-modernbert is an AI model developed by Alibaba (China), first published in January 2025. It works in the language domain, on tasks such as language modeling/generation and question answering.

Training it took an estimated 3.7×10²¹ FLOP of compute (estimation method: operation counting). The model has 149,000,000 parameters. It was trained on roughly 1B datapoints.

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

Full record

Organization: Alibaba
Country of organization: China
Domain: Language
Task: Language modeling/generation, Question answering
Training compute: 3.7×10²¹ FLOP
Compute estimation method: Operation counting
Parameters: 149,000,000
Dataset size: 1B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Likely