Card: list the training data (datasets:, base_model:) and add a Training data section

Follow-up to braindecode PR #1493: `from_pretrained` reads `datasets:` into `model.card_data`. Ids: MOABB names, NEMAR nm/on ids, OpenNeuro ds ids; evidence per checkpoint.

README.md

@@ -9,6 +9,8 @@ tags:
 - foundation-model
 - model_hub_mixin
 - pytorch_model_hub_mixin
+datasets:
+- nm000253
 ---
 
 # BrainBERT — Foundation Model for Intracranial Neural Signals
@@ -74,6 +76,24 @@ freely change `n_chans` and `n_outputs` (the classification head is task-specifi
 and randomly initialized — fine-tune it on your downstream task). `n_times` only
 needs to be long enough to yield at least one spectrogram frame.
 
+<!-- braindecode:training-data -->
+## Training data
+
+The data that shaped these weights. The ids are the `datasets:` field of this card,
+which braindecode reads into `model.card_data.datasets` when you call
+`from_pretrained` (MOABB class names for MOABB datasets, OpenNeuro / NEMAR
+accessions, Hub ids otherwise). `nm`/`on` ids are datasets on [NEMAR](https://nemar.org)
+(`on` = NEMAR's copy of the OpenNeuro dataset with the same number). Rows marked
+`private:` are data the authors did not release; they are not in `datasets:`.
+
+| `datasets:` id | Dataset | Stage | Modality |
+|---|---|---|---|
+| [`nm000253`](https://nemar.org/dataset/nm000253) | [Brain Treebank: large-scale intracranial recordings from naturalistic language stimuli (Wang et al., NeurIPS 2024 D&B; 10 subjects, 26 movie sessions, ~43.5 h sEEG)](https://braintreebank.dev/) | pretraining | iEEG |
+
+- self-supervised masked spectrogram modelling; 19 of 26 sessions (all 10 subjects); 7 sessions held out for decoding tasks
+- Sources: arXiv:2302.14367 (ICLR 2023) p.4, Data; arXiv:2302.14367 p.4-5, Section 3; https://github.com/czlwang/BrainBERT README; arXiv:2411.08343 (Brain Treebank) p.1.
+
+
 ## Usage
 
 ```python