diff --git a/training/configs/dpo_8b.yaml b/training/configs/dpo_8b.yaml
index fa97b8b0..1599c01d 100644
--- a/training/configs/dpo_8b.yaml
+++ b/training/configs/dpo_8b.yaml
@@ -1,14 +1,14 @@
 # MLX DPO Training Configuration for Hermes 4 (8B Class)
 # Optimized for Apple Silicon execution (daily driver capability).
 
-model: "NousResearch/Hermes-4-8B"
+model: "mlx-community/Hermes-3-Llama-3.1-8B-4bit"
 train: true
 
 # Use the curated DPO preference pairs dataset
-data: "data/"
+data: "autolora/data/dpo/"
 
 # Output adapter configuration
-adapter_path: "adapters/dpo_8b_adapter"
+adapter_path: "autolora/adapters/dpo-8b-adapter"
 save_every: 200
 
 # DPO parameters