Model reference · open weights

reve-large

reve-large is an open-weight embedding model from brain-bzh. reve-large (FP32) weighs 780 MB; the smallest configuration that runs it is RTX 3060 12 GB.

• REVE is a transformer-based foundation model for EEG signal processing developed by brain-bzh.
• It features 390M parameters and uses a 4D positional encoding scheme to process signals of arbitrary length and electrode arrangement.
• The model was pretrained on over 60,000 hours of EEG data from 92 datasets and is available under the REVE Responsible Use License v1.0.

Summary of the brain-bzh/reve-large model card, 2026-10-01

Hugging Face ↗Paper ↗