Update README.md

README.md

@@ -2,11 +2,11 @@
 license: cc-by-nc-4.0
 ---
 
-# Model Card for **_Panda_MLM_**
+# Model Card for **_Panda_MLM-66M_**
 
 **_This is a scaled-up version of the Masked Language Model (MLM) checkpoint used in our preprint for the completions task._**
 
-Trained with larger dataset of multiple initial conditions per system, with mixed periods as well.
+Trained with larger dataset of multiple initial conditions per system, with mixed periods as well. 12 layers with 12 attention heads each.
 
 *Panda*: Patched Attention for Nonlinear Dynamics.