Update README.md

README.md

@@ -38,14 +38,14 @@ This model has been **specifically engineered for robust Function Calling**, all
 * **ChatML Native:** Uses the standard `<|im_start|>` format for easy integration.
 * **GGUF Ready:** Available in all quantization levels (from 16-bit down to 2-bit).
 
-  # 📊 Performance Benchmark
+# 📊 Performance Benchmark
 
 <div align="center">
   <img src="./nova_benchmark.jpg" alt="Nova-LFM Benchmark Chart" width="100%" />
 </div>
 
 > **Note:** The "Blind Test" metric (58%) represents the model's raw semantic accuracy without any tool definitions provided (Zero-Shot). The "Syntax Reliability" (97%) measures the model's ability to generate valid, crash-free JSON structure, which matches GPT-4o class performance.
-> 
+>
 
 ---
 
@@ -92,13 +92,14 @@ Expected Output:
 <tool_call>
 {"name": "calculate_circle_area", "arguments": {"radius": 5}}
 </tool_call>
+```
 
-2. Using GGUF (llama.cpp / Ollama)
+### 2. Using GGUF (llama.cpp / Ollama)
 This model is available in GGUF format in the companion repository: NovachronoAI/LFM2.5-1.2B-Nova-Function-Calling-GGUF
  * Recommended: q4_k_m.gguf (Balanced Speed/Quality - ~800MB)
  * Max Quality: f16.gguf (Lossless - ~2.5GB)
  * Max Speed: q2_k.gguf (Extreme Speed - ~400MB)
-⚙️ Training Details
+### ⚙️ Training Details
 | Parameter | Value |
 |---|---|
 | Base Model | LiquidAI/LFM2.5-1.2B-Instruct |