Upload README.md with huggingface_hub

README.md

@@ -16,7 +16,7 @@ pipeline_tag: text-classification
 
 # Modular Multiplication Transformer
 
-A 1-layer, 4-head transformer trained on **(a x b) mod 113** that exhibits **grokking** — delayed generalization after memorization. This checkpoint includes full training history (400 checkpoints across 40,000 epochs).
+A 1-layer, 4-head transformer trained on **(a x b) mod 113** that exhibits **grokking** (delayed generalization after memorization). This checkpoint includes full training history (400 checkpoints across 40,000 epochs).
 
 ## Model Architecture