Model card aligned with the paper

README.md

@@ -10,10 +10,11 @@ tags:
 
 # TabOmics v2
 
-TabOmics is a tabular foundation model for wide omics data. It is pretrained on synthetic tables and uses in-context
-learning: given labelled training rows and unlabelled test rows, it predicts the test rows in a single forward pass,
-with no training or tuning on your data. It is designed for wide tables (thousands of features, few samples, as in
-omics), also works on ordinary tables, and provides row embeddings and feature importance.
+TabOmics is a tabular foundation model for wide omics data. It is pretrained only on synthetic tables and uses
+in-context learning: given labeled training rows and unlabeled test rows, it predicts the test rows in a single forward
+pass, with no training or tuning on your data. It is designed for wide tables (thousands of features, few samples, as
+in omics), processes every feature jointly, also works on ordinary tables, and provides sample embeddings and feature
+importance from the same forward pass.
 
 ```python
 from tabomics import Classifier
@@ -21,4 +22,14 @@ clf = Classifier(model="v2").fit(X_train, y_train)
 proba = clf.predict_proba(X_test)
 ```
 
-Code, documentation and licence: https://github.com/lbotecur/tabomics (GNU General Public License v3.0 or later).
+## Model details
+
+- Classifier of up to 10 classes.
+- A Transformer of 12 blocks, each with attention between features, attention between rows and an MLP;
+  embedding size 192, 6 attention heads, 7.3M parameters.
+- Pretrained only on synthetic tables; the recipes of the published models are in `configs/` of the repository.
+  Standardized features are clipped at 10 at inference.
+- `n_estimators` averages ensemble members: forward passes on copies of the table with the columns reordered and the
+  categories and classes renumbered at random (1 by default).
+
+Code, documentation and license: https://github.com/lbotecur/tabomics (GNU General Public License v3.0 or later).