---
library_name: transformers
tags:
  - eeg
  - neuroscience
  - foundation-model
  - pytorch
license: other
license_name: reve-responsible-use-license-v1.0
license_link: LICENSE

model-index:
- name: Reve-large Evaluation Results
  results:
    - task:
          type: feature-extraction
      dataset:
          name: Mumtaz-LP
          type: Mumtaz-LP
      metrics:
          - type: Accuracy
            value: 0.985
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: MAT-LP
          type: MAT-LP
      metrics:
          - type: Accuracy
            value: 0.712
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: TUAB-LP
          type: TUAB-LP
      metrics:
          - type: Accuracy
            value: 0.821
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: PhysionetMIT-LP
          type: PhysionetMIT-LP
      metrics:
          - type: Accuracy
            value: 0.617
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: BCIC-IV-2a-LP
          type: BCIC-IV-2a-LP
      metrics:
          - type: Accuracy
            value: 0.603
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: ISRUC-LP
          type: ISRUC-LP
      metrics:
          - type: Accuracy
            value: 0.758
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: HMC-LP
          type: HMC-LP
      metrics:
          - type: Accuracy
            value: 0.710
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: BCIC2020-3A-LP
          type: BCIC2020-3A-LP
      metrics:
          - type: Accuracy
            value: 0.390
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: TUEV-LP
          type: TUEV-LP
      metrics:
          - type: Accuracy
            value: 0.630
            name: Accuracy

    - task:
          type: feature-extraction
      dataset:
          name: FACED-LP
          type: FACED-LP
      metrics:
          - type: Accuracy
            value: 0.469
            name: Accuracy
---
# Model Card for REVE-large

<!-- Provide a quick summary of what the model is/does. -->

REVE ([project page here](https://brain-bzh.github.io/reve/)) is a transformer-based foundation model for EEG signal processing. It was trained on 60k hours of EEG data from various sources and is designed to be adaptable to any electrode configuration and a wide range of EEG-based tasks.




## Model Details

### Architecture

<!-- Provide a longer summary of what this model is. -->

REVE (Representation for EEG with Versatile Embeddings), a pretrained encoder explicitly designed to generalize across diverse EEG signals. 
REVE introduces a novel 4D positional encoding scheme that enables it to process signals of arbitrary length and electrode arrangement.
Using a masked autoencoding objective, we pretrain REVE on over 60,000 hours of EEG data from 92 datasets spanning 25,000 subjects.

**Developed by** the [BRAIN team](https://www.imt-atlantique.fr/en/research-innovation/teams/brain) and [UdeM](https://www.umontreal.ca/en/)

**Funded by:** This research was supported by the French National Research Agency (ANR) through its AI@IMT program and grant ANR-24-CE23-7365, as well as by a grant from the Brittany region. Further support was provided by a Discovery Grant from the Natural Sciences and Engineering Research Council of Canada (NSERC), by funding from the Canada Research Chairs program and the Fonds de recherche du Québec – Nature et technologies (FRQ-NT). This work was granted access to the HPC resources of IDRIS under the allocation 2024-AD011015237R1 made by GENCI, as well as HPC provided by Digital Alliance Canada. 

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [github](https://brain-bzh.github.io/reve/)
- **Paper :** [arxiv](https://arxiv.org/abs/2510.21585)

## Uses

Example script to extract embeddings with REVE, using our position bank:
```python
from transformers import AutoModel

pos_bank = AutoModel.from_pretrained("brain-bzh/reve-positions", trust_remote_code=True)
model = AutoModel.from_pretrained("brain-bzh/reve-large", trust_remote_code=True)

eeg_data = ... # EEG data as a torch Tensor (batch_size, channels, time_points), must be sampled at 200 Hz

electrode_names = [...] # List of electrode names corresponding to the channels in eeg_data
positions = pos_bank(electrode_names) # Get positions (channels, 3)
# Expand the positions vector to match the batch size 
positions = positions.expand(eeg_data.size(0), -1, -1)  # (batch_size, channels, 3)

output = model(eeg_data, positions)
```

## License and Responsible Use

REVE is available for research, commercial, educational, and personal use under the **REVE Responsible Use License v1.0**.

By downloading, using, modifying, redistributing, or deploying REVE or a derivative model, you agree to comply with the terms of the [`LICENSE`](./LICENSE).

In particular, the License prohibits privacy intrusion and re-identification, non-consensual surveillance or profiling, discriminatory or harmful uses, and other uses that violate applicable law. Redistribution and publication of fine-tuned or otherwise modified REVE models are permitted, provided that the License, attribution, and provenance requirements are preserved.