Upload README.md with huggingface_hub

README.md

@@ -24,13 +24,13 @@ model-index:
       type: custom
     metrics:
     - type: accuracy
-      value: 0.95
+      value: 95.0
       name: Accuracy
     - type: f1
-      value: 0.945
+      value: 94.5
       name: Harmful F1
     - type: f1
-      value: 0.972
+      value: 97.2
       name: Safe F1
 ---
 
@@ -51,10 +51,10 @@ This model classifies user prompts as **harmful** or **safe** while generating d
 | **Accuracy** | 95.0% |
 | **Harmful Precision** | 93.5% |
 | **Harmful Recall** | 95.6% |
-| **Harmful F1** | 0.945 |
+| **Harmful F1** | 94.5% |
 | **Safe Precision** | 100.0% |
 | **Safe Recall** | 94.5% |
-| **Safe F1** | 0.972 |
+| **Safe F1** | 97.2% |
 
 ### Confusion Matrix
 ```