Update README.md

README.md

@@ -64,26 +64,35 @@ Such categorization supports **policy analysis, thematic mapping of central bank
 * GPU: Tesla T4 (16GB)
 * Framework: PyTorch 2.8.0 + Hugging Face Transformers
 
+## Evaluation Results
 
-## Evaluation
+| Split      | Accuracy  | Macro-F1  | Weighted-F1 | Class            | Precision | Recall | F1    |
+| ---------- | --------- | --------- | ----------- | ---------------- | --------- | ------ | ----- |
+| Validation | **0.851** | **0.839** | **0.852**   | –                | –         | –      | –     |
+| Test       | **0.823** | **0.803** | **0.825**   | **Feature**      | 0.759     | 0.782  | 0.770 |
+|            |           |           |             | **Process**      | 0.927     | 0.845  | 0.884 |
+|            |           |           |             | **Risk-Benefit** | 0.700     | 0.817  | 0.754 |
 
-### Validation (10%)
 
-* Accuracy: **0.851**
-* Macro-F1: **0.839**
-* Weighted-F1: **0.852**
+---
 
-### Test (10%)
+## How to Use
 
-* Accuracy: **0.823**
-* Macro-F1: **0.803**
-* Weighted-F1: **0.825**
+```python
+from transformers import pipeline
 
-#### Per-class performance (Test)
+# Load pipeline
+classifier = pipeline("text-classification", model="bilalzafar/CBDC-Discourse")
 
-| Class        | Precision | Recall | F1    |
-| ------------ | --------- | ------ | ----- |
-| Feature      | 0.759     | 0.782  | 0.770 |
-| Process      | 0.927     | 0.845  | 0.884 |
-| Risk-Benefit | 0.700     | 0.817  | 0.754 |
+# Example sentences
+sentences = [
+    "The central bank launched a pilot project for CBDC cross-border settlement.",
+    "Programmability in CBDC allows conditional payments.",
+    "CBDC may increase risks of bank disintermediation."
+]
 
+# Predict
+for s in sentences:
+    result = classifier(s, return_all_scores=False)[0]
+    print(f"{s}\n → {result['label']} (score={result['score']:.4f})\n")
+    ```