--- pipeline_tag: feature-extraction tags: - eeg - brain-computer-interface - self-supervised-learning - mamba - pytorch --- # SAMBA-100s [Project website](https://samba.dcode.ai/) · [Code](https://github.com/Jiazhen-Hong/SAMBA) · [Paper](https://arxiv.org/abs/2511.18571) · [SAMBA-2s](https://huggingface.co/Dcode-AI/SAMBA-2s) SAMBA-100s was pretrained on 100-second windows from the Temple University Hospital Abnormal EEG Corpus (TUAB), using 12,800 samples at 128 Hz and 16 bipolar channels. Retraining followed the original method with a rebuilt TUAB pipeline and validation split. The encoder supports other window lengths and electrode layouts. ## Download [Download config](https://huggingface.co/Dcode-AI/SAMBA-100s/resolve/main/config.json?download=true) · [Download weights](https://huggingface.co/Dcode-AI/SAMBA-100s/resolve/main/model.safetensors?download=true) Keep both files in the same directory. To download them together from a terminal: ```bash pip install -U huggingface_hub hf download Dcode-AI/SAMBA-100s config.json model.safetensors --local-dir ./SAMBA-100s ``` ## Usage Install SAMBA in a CUDA environment: ```bash git clone https://github.com/Jiazhen-Hong/SAMBA.git cd SAMBA pip install -e '.[mamba,hub]' ``` Load the downloaded directory. If you skipped the download step, the following example fetches both files automatically: ```python import torch from huggingface_hub import snapshot_download from samba_eeg import SambaModel folder = snapshot_download( "Dcode-AI/SAMBA-100s", allow_patterns=["config.json", "model.safetensors"], ) model = SambaModel.from_pretrained(folder).cuda().eval() ``` For files you already downloaded, pass their local directory to `SambaModel.from_pretrained` in place of `folder`. Prepare EEG at 128 Hz. Use `signals` shaped `[batch, channels, samples]` and electrode `positions` shaped `[channels, 3]` or `[batch, channels, 3]`. Match the signal channel order and use the same coordinate frame and units as the target positions in `config.json`. TUAB pretraining used a 0.5–45 Hz bandpass. The decoder reconstructs EEG on a fixed 16-channel bipolar montage. ```python signals = signals.to(device="cuda", dtype=torch.float32) positions = positions.to(device="cuda", dtype=torch.float32) # Skip these two lines if the signals are already normalized this way. scale = torch.quantile(signals.abs(), 0.95, dim=-1, keepdim=True) signals = signals / scale.clamp_min(1e-8) with torch.inference_mode(): features = model.encode(signals, positions) pooled_features = features.mean(dim=1) ``` `features` has shape `[batch, floor(samples / 8), 128]`. Use `pooled_features` for linear probing. ## Learned EEG spatial weights SAMBA uses electrode coordinates to learn how to combine EEG channels. These maps show how the spatial weights change during training. | Eyes open vs. closed | Driver distraction | Motor imagery | |:---:|:---:|:---:| | Eyes open vs. closed | Driver distraction | Motor imagery | ## Citation ```bibtex @inproceedings{hong2026samba, title = {{SAMBA}: Toward an {EEG} Foundation Model via Differential Mamba and Coordinate-Driven Spatial Embedding}, author = {Hong, Jiazhen and Mackellar, Geoffrey and Ghane, Soheila}, booktitle = {NeurReps 2026: Symmetry and Geometry in Neural Representations (Proceedings Track)}, year = {2026} } ```