Update orfb-design/MODEL_CARD.md

orfb-design/MODEL_CARD.md

@@ -11,7 +11,7 @@ tags:
 
 # Graphormer Redox Predictors
 
-**Last updated:** 30-SEP-2026
+**Last updated:** 10-NOV-2026
 
 ## Model summary
 
@@ -19,7 +19,7 @@ tags:
 | --- | --- |
 | Developer | Microsoft Corporation |
 | Description | Two non-generative molecular property regression models that estimate one-electron reduction or oxidation potential, in volts versus the standard hydrogen electrode, from a molecule represented as SMILES. |
-| Model architecture | Six-layer graph Transformer encoder with 768-dimensional embedding, 32 attention heads, and a scalar regression head. |
+| Model architecture | Twelve-layer Graphormer encoder (`graphormer_base`) with 768-dimensional embedding, 32 attention heads, and a scalar regression head. |
 | Parameters | 1-500M |
 | Inputs | SMILES molecular strings; up to 128 non-hydrogen atoms per molecule. |
 | Outputs | A scalar reduction or oxidation potential per valid molecule. |