bruAristimunha commited on
Commit
47d4521
·
verified ·
1 Parent(s): 269f98c

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

Browse files

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.

Files changed (1) hide show
  1. README.md +21 -1
README.md CHANGED
@@ -10,8 +10,9 @@ tags:
10
  - population-transformer
11
  - pytorch_model_hub_mixin
12
  - model_hub_mixin
13
- base_model: PopulationTransformer/popt_brainbert_stft
14
  pipeline_tag: feature-extraction
 
 
15
  ---
16
 
17
  # PopulationTransformer (PopT) — braindecode weights
@@ -61,6 +62,25 @@ layer on the `CLS` token, as upstream's `PtDownstreamModel.linear_out`) is
61
  | activation | GELU |
62
  | parameters (encoder + spec head) | ~20.0M |
63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  ## Usage
65
 
66
  ```python
 
10
  - population-transformer
11
  - pytorch_model_hub_mixin
12
  - model_hub_mixin
 
13
  pipeline_tag: feature-extraction
14
+ datasets:
15
+ - nm000253
16
  ---
17
 
18
  # PopulationTransformer (PopT) — braindecode weights
 
62
  | activation | GELU |
63
  | parameters (encoder + spec head) | ~20.0M |
64
 
65
+ <!-- braindecode:training-data -->
66
+ ## Training data
67
+
68
+ The data that shaped these weights. The ids are the `datasets:` field of this card,
69
+ which braindecode reads into `model.card_data.datasets` when you call
70
+ `from_pretrained` (MOABB class names for MOABB datasets, OpenNeuro / NEMAR
71
+ accessions, Hub ids otherwise). `nm`/`on` ids are datasets on [NEMAR](https://nemar.org)
72
+ (`on` = NEMAR's copy of the OpenNeuro dataset with the same number). Rows marked
73
+ `private:` are data the authors did not release; they are not in `datasets:`.
74
+
75
+ | `datasets:` id | Dataset | Stage | Modality |
76
+ |---|---|---|---|
77
+ | [`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, pretraining | iEEG |
78
+
79
+ - frozen per-channel front end: BrainBERT stft_large_pretrained (itself pretrained on Brain Treebank)
80
+ - PopT self-supervised pretraining on BrainBERT features; 19 of 26 movies (same 10 subjects), 7 held out for downstream
81
+ - Sources: https://huggingface.co/PopulationTransformer/popt_brainbert_stft README; arXiv:2406.03044 (ICLR 2025) p.5, Section 4; https://github.com/czlwang/PopulationTransformer README.
82
+
83
+
84
  ## Usage
85
 
86
  ```python