Add pipeline tag and sample usage

README.md

@@ -1,29 +1,19 @@
 ---
-license: cc-by-nd-4.0
-language:
-- en
-library_name: pytorch
-tags:
-- eeg
-- biosignal
-- mamba
-- state-space-model
-- cross-attention
-- foundation-model
-- self-supervised
-- masked-modeling
-- lejepa
-- topology-invariant
-- neuroscience
 datasets:
 - TUEG
 - TUAB
+- TUSL
+- TUAR
 - APAVA
 - TDBrain
 - MoBI
 - SEED-V
 - Mumtaz2016
 - MODMA
+language:
+- en
+library_name: pytorch
+license: cc-by-nd-4.0
 metrics:
 - balanced_accuracy
 - roc_auc
@@ -31,140 +21,152 @@ metrics:
 - r2
 - pearson_r
 - cohen_kappa
+- rmse
+pipeline_tag: other
+tags:
+- eeg
+- biosignal
+- mamba
+- state-space-model
+- cross-attention
+- foundation-model
+- self-supervised
+- masked-modeling
+- lejepa
+- topology-invariant
+- neuroscience
 thumbnail: https://raw.githubusercontent.com/pulp-bio/BioFoundation/refs/heads/main/docs/model/logo/LuMamba_logo.png
 model-index:
-  - name: LuMamba-Tiny (LeJEPA-reconstruction pre-training)
-    results:
-      - task:
-          type: time-series-classification
-          name: EEG Abnormality Detection
-        dataset:
-          type: TUAB
-          name: TUH EEG Abnormal Corpus (TUAB)
-        metrics:
-          - type: balanced_accuracy
-            value: 80.99
-            name: Balanced Accuracy (%)
-          - type: roc_auc
-            value: 0.883
-            name: AUROC
-          - type: pr_auc
-            value: 0.892
-            name: AUC-PR
-      - task:
-          type: time-series-classification
-          name: Alzheimer's Disease Detection
-        dataset:
-          type: APAVA
-          name: APAVA
-        metrics:
-          - type: roc_auc
-            value: 0.955
-            name: AUROC
-          - type: pr_auc
-            value: 0.970
-            name: AUC-PR
-      - task:
-          type: time-series-classification
-          name: Parkinson's Disease Detection
-        dataset:
-          type: TDBrain
-          name: TDBrain
-        metrics:
-          - type: roc_auc
-            value: 0.961
-            name: AUROC
-          - type: pr_auc
-            value: 0.960
-            name: AUC-PR
-      - task:
-          type: time-series-classification
-          name: Major Depressive Disorder Detection
-        dataset:
-          type: Mumtaz2016
-          name: Mumtaz2016
-        metrics:
-          - type: roc_auc
-            value: 0.931
-            name: AUROC
-          - type: pr_auc
-            value: 0.952
-            name: AUC-PR
-  - name: LuMamba-Tiny (Reconstruction-only pre-training)
-    results:
-      - task:
-          type: time-series-classification
-          name: EEG Slowing Event and Seizure Detection
-        dataset:
-          type: TUSL
-          name: TUH EEG Slowing Corpus (TUSL)
-        metrics:
-          - type: roc_auc
-            value: 0.708
-            name: AUROC
-          - type: pr_auc
-            value: 0.289
-            name: AUC-PR
-      - task:
-          type: time-series-classification
-          name: EEG Artifact Detection
-        dataset:
-          type: TUAR
-          name: TUH EEG Artifact Corpus (TUAR)
-        metrics:
-          - type: roc_auc
-            value: 0.914
-            name: AUROC
-          - type: pr_auc
-            value: 0.510
-            name: AUC-PR
-      - task:
-          type: time-series-classification
-          name: Gait Prediction Regression
-        dataset:
-          type: MoBI
-          name: MoBI
-        metrics:
-          - type: r2
-            value: 0.116
-            name: R-squared
-          - type: rmse
-            value: 0.1482
-            name: Root Mean Squared Error
-      - task:
-          type: time-series-classification
-          name: 5-class Emotion Detection
-        dataset:
-          type: SEED-V
-          name: SEED-V
-        metrics:
-          - type: balanced_accuracy
-            value: 35.0
-            name: Balanced Accuracy (%)
-          - type: cohen_kappa
-            value: 0.191
-            name: Cohen's Kappa
-      - task:
-          type: time-series-classification
-          name: Major Depressive Disorder Detection
-        dataset:
-          type: MODMA
-          name: MODMA
-        metrics:
-          - type: balanced_accuracy
-            value: 59.5
-            name: Balanced Accuracy (%)
-          - type: roc_auc
-            value: 0.448
-            name: AUROC
-          - type: pr_auc
-            value: 0.420
-            name: AUC-PR
+- name: LuMamba-Tiny (Reconstruction-only pre-training)
+  results:
+  - task:
+      type: time-series-classification
+      name: EEG Abnormality Detection
+    dataset:
+      name: TUH EEG Abnormal Corpus (TUAB)
+      type: TUAB
+    metrics:
+    - type: balanced_accuracy
+      value: 80.99
+      name: Balanced Accuracy (%)
+    - type: roc_auc
+      value: 0.883
+      name: AUROC
+    - type: pr_auc
+      value: 0.892
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: Alzheimer's Disease Detection
+    dataset:
+      name: APAVA
+      type: APAVA
+    metrics:
+    - type: roc_auc
+      value: 0.955
+      name: AUROC
+    - type: pr_auc
+      value: 0.97
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: Parkinson's Disease Detection
+    dataset:
+      name: TDBrain
+      type: TDBrain
+    metrics:
+    - type: roc_auc
+      value: 0.961
+      name: AUROC
+    - type: pr_auc
+      value: 0.96
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: Major Depressive Disorder Detection
+    dataset:
+      name: Mumtaz2016
+      type: Mumtaz2016
+    metrics:
+    - type: roc_auc
+      value: 0.931
+      name: AUROC
+    - type: pr_auc
+      value: 0.952
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: EEG Slowing Event and Seizure Detection
+    dataset:
+      name: TUH EEG Slowing Corpus (TUSL)
+      type: TUSL
+    metrics:
+    - type: roc_auc
+      value: 0.708
+      name: AUROC
+    - type: pr_auc
+      value: 0.289
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: EEG Artifact Detection
+    dataset:
+      name: TUH EEG Artifact Corpus (TUAR)
+      type: TUAR
+    metrics:
+    - type: roc_auc
+      value: 0.914
+      name: AUROC
+    - type: pr_auc
+      value: 0.51
+      name: AUC-PR
+  - task:
+      type: time-series-classification
+      name: Gait Prediction Regression
+    dataset:
+      name: MoBI
+      type: MoBI
+    metrics:
+    - type: r2
+      value: 0.116
+      name: R-squared
+    - type: rmse
+      value: 0.1482
+      name: Root Mean Squared Error
+  - task:
+      type: time-series-classification
+      name: 5-class Emotion Detection
+    dataset:
+      name: SEED-V
+      type: SEED-V
+    metrics:
+    - type: balanced_accuracy
+      value: 35.0
+      name: Balanced Accuracy (%)
+    - type: cohen_kappa
+      value: 0.191
+      name: Cohen's Kappa
+  - task:
+      type: time-series-classification
+      name: Major Depressive Disorder Detection
+    dataset:
+      name: MODMA
+      type: MODMA
+    metrics:
+    - type: balanced_accuracy
+      value: 59.5
+      name: Balanced Accuracy (%)
+    - type: roc_auc
+      value: 0.448
+      name: AUROC
+    - type: pr_auc
+      value: 0.42
+      name: AUC-PR
 ---
+
 <div align="center">
   <img src="https://raw.githubusercontent.com/pulp-bio/BioFoundation/refs/heads/main/docs/model/logo/LuMamba_logo.png" alt="LuMamba Logo" width="800"/>
-  <h1>LuMamba: Latent Unified Mamba for Electrode
-Topology-Invariant and Efficient EEG Modeling</h1>
+  <h1>LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling</h1>
 </div>
 <p align="center">
   <a href="https://github.com/pulp-bio/BioFoundation">
@@ -184,6 +186,27 @@ LuMamba addresses varying channel layouts with **LUNA channel unification**, pro
 
 ---
 
+## 🔧 Sample Usage
+
+### Download Weights
+You can download all pre-trained variants and safetensors programmatically using `huggingface_hub`:
+
+```python
+from huggingface_hub import snapshot_download
+
+# downloads all pre-trained variants and safetensors into ./checkpoints/LuMamba
+snapshot_download(repo_id="PulpBio/LuMamba", repo_type="model", local_dir="checkpoints/LuMamba")
+```
+
+### Fine-tuning
+Include the safetensors checkpoint path as input and run fine-tuning in the command line:
+```bash
+python -u run_train.py +experiment=LuMamba_finetune \
+  pretrained_safetensors_path=/absolute/path/to/checkpoints/LuMamba/LuMamba.safetensors
+```
+
+---
+
 ## 🔒 License & Usage Policy (Weights)
 
 **Weights license:** The released model weights are licensed under **Creative Commons Attribution–NoDerivatives 4.0 (CC BY-ND 4.0)**. This section summarizes the practical implications for users. *This is not legal advice; please read the full license text.*
@@ -214,7 +237,7 @@ We welcome community improvements via a **pull-request (PR)** workflow. If you b
 - **Goal:** Efficient and topology-agnostic EEG modeling with linear complexity in sequence length.
 - **Core idea:** **Channel-Unification Module** uses **learned queries** (Q) with **cross-attention** to map any set of channels to a fixed latent space. **bidirectional Mamba blocks** then operate on that latent sequence.
 - **Pre-training data:** TUEG, **>21,000 hours** of raw EEG; downstream subjects removed to avoid leakage.
-- **Downstream tasks:** **TUAB** (abnormal), **TUAR** (artifacts), **TUSL** (slowing), **SEED-V** (emotion; unseen 62-ch montage), **APAVA** (Alzheimer's disease; unseen 16-ch layout, **TDBrain** (Parkinson's disease; unseen 26-ch layout)
+- **Downstream tasks:** **TUAB** (abnormal), **TUAR** (artifacts), **TUSL** (slowing), **SEED-V** (emotion; unseen 62-ch montage), **APAVA** (Alzheimer's disease; unseen 16-ch layout), **TDBrain** (Parkinson's disease; unseen 26-ch layout)
 
 ---
 
@@ -271,22 +294,6 @@ Larger model sizes can be attained by increasing the number of bi-Mamba blocks `
 
 ---
 
-## 🔧 How to Use
-
-LuMamba weights are organized by pre-training configuration:
-
-- **`Reconstruction-only`** → variants pre-trained with masked reconstruction exclusively  
-- **`LeJEPA-reconstruction`** → variants pre-trained with a balanced mixture of masked reconstruction and LeJEPA losses. Variants exist for two different LeJEPA hyperparameters: 128 and 300 projection slices.
-- **`LeJEPA-only`** → variant pre-trained with LeJEPA exclusively.
-
-All variants are pre-trained on TUEG.
-
-LuMamba experiments are categorized by two Hydra configurations, in `BioFoundation/config/experiments`:
-- **`LuMamba_finetune.yaml`** → configuration for fine-tuning experiments.
-- **`LuMamba_pretrain.yaml`** → configuration for pre-training experiments.
-
----
-
 ## 🔧 Fine-tuning — General Checklist
 
 0. **Install & read data prep**: clone the [BioFoundation repo](https://github.com/pulp-bio/BioFoundation), set up the environment as described there, then open `make_datasets/README.md` for dataset-specific notes (naming, expected folder layout, and common pitfalls).
@@ -305,13 +312,6 @@ LuMamba experiments are categorized by two Hydra configurations, in `BioFoundati
 6. **Trainer/optimizer**: adjust `gpus/devices`, `batch_size`, `max_epochs`, LR/scheduler if needed.
 7. **I/O**: set `io.base_output_path` and confirm `io.checkpoint_dirpath` exists.
 
-
-To launch fine-tuning (Hydra):
-
-```bash
-python -u run_train.py +experiment=LuMamba_finetune
-```
-
 ---
 
 ## ⚖️ Responsible AI, Risks & Biases
@@ -325,7 +325,7 @@ python -u run_train.py +experiment=LuMamba_finetune
 ## 🔗 Sources
 
 - **Code:** https://github.com/pulp-bio/BioFoundation  
-- **Paper:** LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling (arxiv:2603.19100)
+- **Paper:** [LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling](https://arxiv.org/abs/2603.19100)
 
 ---
 
@@ -343,23 +343,4 @@ If you use LuMamba, please cite:
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2603.19100}, 
 }
-```
-
----
-
-## 🛠️ Maintenance & Contact
-
-- **Issues & support:** please open a GitHub issue in the BioFoundation repository.
-
----
----
-
-## 🔗 Related Models
-
-- **[LUNA](https://huggingface.co/PulpBio/LUNA)** — Transformer-based topology-agnostic EEG foundation model (NeurIPS 2025). Source of the channel-unification cross-attention module that LuMamba reuses.
-- **[FEMBA](https://huggingface.co/PulpBio/FEMBA)** — Bidirectional Mamba foundation model for EEG. Source of the linear-complexity temporal backbone that LuMamba reuses.
-- **[TinyMyo](https://huggingface.co/PulpBio/TinyMyo)** — Tiny foundation model for flexible EMG signal processing at the edge.
-  
-## 🗒️ Changelog
-
-- **v1.0:** Initial release of LuMamba model card with task-specific checkpoints and instructions.
+```