Update README.md

README.md

@@ -78,7 +78,7 @@ This model has been optimized using [Unsloth](https://github.com/unslothai/unslo
 ALLaM-Thinking was trained using a combination of techniques:
 
 - Base architecture fine-tuned on diverse Arabic datasets
-- GRPO (Generalized Reinforced Preference Optimization) for better alignment
+- GRPO (Group Relative Policy Optimization) for better alignment
 - Specialized training on mathematical reasoning and step-by-step problem-solving
 
 ## Performance