Update README.md

README.md

@@ -10,12 +10,12 @@ tags:
 ---
 # Dante-Zero Fine-tuned Model
 
-This model was fine-tuned using Reinforcement Learning with Generative Pre-trained Transformer Optimization (GRPO) to generate Dante-style poetry in endecasillabi (11-syllable lines).
+This model was fine-tuned using Reinforcement Learning with Group Relative Policy Optimization (GRPO) to generate Dante-style poetry in endecasillabi (11-syllable lines).
 
 ## Model Details
 
 - **Base Model:** PleIAs/Pleias-350m-Preview
-- **Training Method:** GRPO (Generative Pre-trained Transformer Optimization)
+- **Training Method:** GRPO (Group Relative Policy Optimization )
 - **Training Data:** 1,000 chunks from Dante's Divine Comedy
 - **Epochs:** 10
 - **Trained By:** ruggsea