Update README.md

README.md

@@ -107,6 +107,7 @@ with torch.no_grad():
 ---
 🔧 Expert Routing
 ---
+
 This model uses a top-2 gating mechanism where, for each token, two of the eight experts are selected based on learned router logits.
 
 During training, a light auxiliary loss was applied to encourage balanced expert usage and improve routing stability.
@@ -116,12 +117,15 @@ Note: Routing logits are optionally available in the model outputs via output_ro
 ---
 📃 License
 ---
+
 This model is released under the Apache 2.0 License.
+
 ---
 🙌 Acknowledgements
 ---
 Trained using:
 ---
+
 🧨 Hugging Face Transformers
 
 🧠 Custom training loop with gradient checkpointing
@@ -129,9 +133,10 @@ Trained using:
 🧮 NVIDIA RTX 4090 (24GB VRAM) / A100 (40GB)
 
 📦 Logged and tracked via Weights & Biases
+
 ---
-### 🗣️ Citation
 
+### 🗣️ Citation
 ---
 @misc{loggenix-moe-0.12B-A0.08B-e5-lr5e4-b4-3060,
   title = {loggenix-moe-0.12B-A0.08B-e5-lr5e4-b4-3060: A Lightweight Mixture-of-Experts Model},