Re-upload checkpoint in flat state_dict layout.

The previous layout nested the encoder and contextualizer under
`encoder_state_dict` / `contextualizer_state_dict` top-level keys, which braindecode's loader did not unwrap: `load_state_dict(..., strict=False)` silently matched 0 of 99 weights and every call to `BENDR.from_pretrained` returned a random model. The flat layout matches braindecode's `BENDR` key namespace (`encoder.encoder.*`, `contextualizer.*`, plus the random classification head), so `from_pretrained(..., strict=True, n_outputs=2)` now loads all 99 pretrained weights. See braindecode PR #992.

README.md

@@ -1,106 +1,14 @@
 ---
-license: apache-2.0
-datasets:
-  - Sleep-EDF
-  - TUAB
-  - MOABB
-language:
-  - en
+library_name: braindecode
+license: bsd-3-clause
 tags:
-  - eeg
-  - brain
-  - timeseries
-  - self-supervised
-  - transformer
-  - biomedical
-  - neuroscience
+- BENDR
+- braindecode
+- model_hub_mixin
+- pytorch_model_hub_mixin
 ---
 
-# BENDR: BErt-inspired Neural Data Representations
-
-Pretrained BENDR model for EEG classification tasks. This is the official Braindecode implementation
-of BENDR from Kostas et al. (2021).
-
-## Model Details
-
-- **Model Type**: Transformer-based EEG encoder
-- **Pretraining**: Self-supervised learning on masked sequence reconstruction
-- **Architecture**: 
-  - Convolutional Encoder: 6 blocks with 512 hidden units
-  - Transformer Contextualizer: 8 layers, 8 attention heads
-  - Total Parameters: ~157M
-- **Input**: Raw EEG signals (20 channels, variable length)
-- **Output**: Contextualized representations or class predictions
-
-## Usage
-
-```python
-from braindecode.models import BENDR
-import torch
-
-# Load pretrained model
-model = BENDR(n_chans=20, n_outputs=2)
-
-# Load pretrained weights from Hugging Face
-from huggingface_hub import hf_hub_download
-checkpoint_path = hf_hub_download(repo_id="braindecode/bendr-pretrained-v1", filename="pytorch_model.bin")
-checkpoint = torch.load(checkpoint_path)
-model.load_state_dict(checkpoint["model_state_dict"], strict=False)
-
-# Use for inference
-model.eval()
-with torch.no_grad():
-    eeg_data = torch.randn(1, 20, 600)  # (batch, channels, time)
-    predictions = model(eeg_data)
-```
-
-## Fine-tuning
-
-```python
-import torch
-from torch.optim import Adam
-
-# Freeze encoder for transfer learning
-for param in model.encoder.parameters():
-    param.requires_grad = False
-
-# Fine-tune on downstream task
-optimizer = Adam(model.parameters(), lr=0.0001)
-```
-
-## Paper
-
-[BENDR: Using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data](https://doi.org/10.3389/fnhum.2021.653659)
-
-Kostas, D., Aroca-Ouellette, S., & Rudzicz, F. (2021).
-Frontiers in Human Neuroscience, 15, 653659.
-
-## Citation
-
-```bibtex
-@article{kostas2021bendr,
-  title={BENDR: Using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data},
-  author={Kostas, Demetres and Aroca-Ouellette, St{\'e}phane and Rudzicz, Frank},
-  journal={Frontiers in Human Neuroscience},
-  volume={15},
-  pages={653659},
-  year={2021},
-  publisher={Frontiers}
-}
-```
-
-## Implementation Notes
-
-- Start token is correctly extracted at index 0 (BERT [CLS] convention)
-- Uses T-Fixup weight initialization for stability
-- Includes LayerDrop for regularization
-- All architectural improvements from original paper maintained
-
-## License
-
-Apache 2.0
-
-## Authors
-
-- Braindecode Team
-- Original paper: Kostas et al. (2021)
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://braindecode.org
+- Paper: [More Information Needed]
+- Docs: https://braindecode.org/stable/generated/braindecode.models.BENDR.html

config.json

@@ -1,16 +1,19 @@
 {
-  "model_type": "bendr",
   "n_chans": 20,
+  "n_outputs": 2,
+  "n_times": 1000,
+  "chs_info": null,
+  "input_window_seconds": null,
+  "sfreq": 250,
   "encoder_h": 512,
   "contextualizer_hidden": 3076,
-  "transformer_heads": 8,
-  "transformer_layers": 8,
-  "position_encoder_length": 25,
+  "projection_head": false,
   "drop_prob": 0.1,
   "layer_drop": 0.0,
-  "start_token": -5,
-  "final_layer": true,
-  "projection_head": false,
+  "activation": "torch.nn.modules.activation.GELU",
+  "transformer_layers": 8,
+  "transformer_heads": 8,
+  "position_encoder_length": 25,
   "enc_width": [
     3,
     2,
@@ -27,6 +30,10 @@
     2,
     2
   ],
-  "notes": "Pretrained BENDR model for EEG classification",
-  "paper": "https://doi.org/10.3389/fnhum.2021.653659"
+  "start_token": -5,
+  "final_layer": true,
+  "encoder_only": false,
+  "n_chans_pretrained": null,
+  "chan_proj_max_norm": 1.0,
+  "braindecode_version": "1.5.0dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4b432a3206cce274d060aa35286592c47e51181b55b71e791f4515ca6752a5
+size 628580476

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58696d59ae4fb3d041837746c6c6225fa851841f68753e8cc28d4ecd4383d828
-size 628594288
+oid sha256:1157d9c148850a91443093cc483ee98339a5f25b7948d4386c46de77131fb5c0
+size 628611067