bruAristimunha commited on
Commit
d11a8bf
·
verified ·
1 Parent(s): 96f612e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +39 -10
README.md CHANGED
@@ -1,14 +1,43 @@
1
  ---
 
 
2
  library_name: braindecode
3
- license: bsd-3-clause
4
- tags:
5
- - MVPFormer
6
- - braindecode
7
- - model_hub_mixin
8
- - pytorch_model_hub_mixin
9
  ---
10
 
11
- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
12
- - Code: https://braindecode.org
13
- - Paper: [More Information Needed]
14
- - Docs: https://braindecode.org/stable/generated/braindecode.models.MVPFormer.html
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags: [braindecode, eeg, ieeg, mvpformer, seizure-detection]
4
  library_name: braindecode
 
 
 
 
 
 
5
  ---
6
 
7
+ # MVPFormer-S seizure detector (SWEC)
8
+
9
+ MVPFormer-S with its SWEC LoRA adapters merged in and the seizure classification head attached. Ready for inference.
10
+
11
+ ```python
12
+ from braindecode.models import MVPFormer
13
+
14
+ model = MVPFormer.from_pretrained("braindecode/mvpformer-s-swec")
15
+ ```
16
+
17
+ Outputs 2 classes (non-seizure, seizure).
18
+
19
+ ## Licence and intended use
20
+
21
+ Weights © IBM Corp. 2024-2025, released under Apache-2.0 (`SPDX-License-Identifier: Apache-2.0`)
22
+ by <https://github.com/IBM/multi-variate-parallel-transformer>. Redistributed here unmodified in
23
+ substance; only the parameter names were remapped onto braindecode's `MVPFormer`.
24
+
25
+ The authors attach the following restriction, reproduced verbatim from the upstream README:
26
+
27
+ > This software may only be used for research. For other applications any liability is denied.
28
+ > In particular, the software must not be used for diagnostic purposes.
29
+
30
+ The paper's broader-impact statement adds: "both our model and our dataset are developed purely
31
+ for research, and may not be used for any other purpose, especially diagnostic."
32
+
33
+ ## Citation
34
+
35
+ ```bibtex
36
+ @article{carzaniga2025foundation,
37
+ title={A foundation model with multi-variate parallel attention to generate neuronal activity},
38
+ author={Carzaniga, Francesco and Hersche, Michael and Sebastian, Abu and Schindler, Kaspar and Rahimi, Abbas},
39
+ journal={arXiv preprint arXiv:2506.20354},
40
+ year={2025}
41
+ }
42
+ ```
43
+