Update README.md

README.md

@@ -3,6 +3,12 @@ license: apache-2.0
 datasets:
 - strangerguardhf/NSFW-MultiDomain-Classification-v2.0
 ---
+# **vit-mini-explicit-content**
+
+> **vit-mini-explicit-content** is an image classification vision-language model fine-tuned from **vit-base-patch16-224-in21k** for a single-label classification task. It categorizes images based on their explicitness using the **ViTForImageClassification** architecture.
+
+> \[!Note]
+> This model is designed to promote safe, respectful, and responsible online spaces. It does **not** generate explicit content; it only classifies images. Misuse may violate platform or regional policies and is strongly discouraged.
 
 ```py
 Classification Report:
@@ -20,3 +26,85 @@ Extincing & Sensual     0.9245    0.9717    0.9475      5618
 ```
 
 ![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/VaSWP4-JjXrczImMGufQE.png)
+
+---
+
+The model categorizes images into five classes:
+
+* **Class 0:** Anime Picture
+* **Class 1:** Enticing & Sensual
+* **Class 2:** Hentai
+* **Class 3:** Pornography
+* **Class 4:** Safe for Work
+
+# **Run with Transformers 🤗**
+
+```python
+!pip install -q transformers torch pillow gradio
+```
+
+```python
+import gradio as gr
+from transformers import ViTImageProcessor, ViTForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/vit-mini-explicit-content"  # Updated model path
+model = ViTForImageClassification.from_pretrained(model_name)
+processor = ViTImageProcessor.from_pretrained(model_name)
+
+# Updated label mapping
+labels = {
+    "0": "Anime Picture",
+    "1": "Enticing & Sensual",
+    "2": "Hentai",
+    "3": "Pornography",
+    "4": "Safe for Work"
+}
+
+def explicit_content_detection(image):
+    """Predicts the type of content in the image."""
+    image = Image.fromarray(image).convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
+
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
+    
+    return predictions
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=explicit_content_detection,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Prediction Scores"),
+    title="vit-mini-explicit-content",
+    description="Upload an image to classify whether it is anime, enticing & sensual, hentai, pornographic, or safe for work."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()
+```
+
+---
+
+# **Recommended Use Cases**
+
+* Image moderation pipelines
+* Parental and institutional content filters
+* Dataset cleansing before training
+* Online safety and well-being platforms
+* Enhancing search engine filtering
+
+# **Discouraged / Prohibited Use**
+
+* Non-consensual or malicious monitoring
+* Automated judgments without human review
+* Misrepresentation of moderation systems
+* Use in unlawful or unethical surveillance
+* Harassment, exploitation, or shaming