Update model card with parameter count clarification

README.md

@@ -8,24 +8,37 @@ tags:
   - 1.58-bit
   - phi-4
   - experimental
+  - 14b-architecture
 library_name: safetensors
 pipeline_tag: text-generation
 language:
   - en
+model_name: Phi-4-BitNet-1.58b
+datasets: []
+metrics: []
 ---
 
 # Phi-4-BitNet-1.58b
 
-BitNet 1.58-bit ternary quantization of Microsoft's Phi-4 14B model.
+**Architecture: 14.7 Billion Parameters** | BitNet 1.58-bit Ternary Quantization
+
+---
+
+> **IMPORTANT: Parameter Count Display**
+>
+> HuggingFace displays a reduced parameter count because it counts packed bytes, not actual parameters.
+> This model has the **full 14.7B parameter Phi-4 architecture**.
+> The weights are stored as ternary values ({-1, 0, +1}) packed 4 per byte, which reduces
+> storage to 4.6 GB but preserves all 14.7 billion parameters.
+
+---
 
 ## Overview
 
-This is an **experimental** BitNet 1.58-bit quantization of the Phi-4 model using absmean scaling with group-wise quantization. The model stores weights as ternary values ({-1, 0, +1}) packed 4 values per byte.
+This is an **experimental** BitNet 1.58-bit quantization of Microsoft's Phi-4 model using absmean scaling with group-wise quantization. The model stores weights as ternary values ({-1, 0, +1}) packed 4 values per byte.
 
 **This is research/experimental work. Quality and performance have not been formally benchmarked.**
 
-> **Note on Parameter Count**: HuggingFace may display a reduced parameter count because the quantized weights are packed (4 values per byte). The model retains the full 14B parameter architecture - only the weight storage is compressed.
-
 ## Specifications
 
 | Property | Value |