Upload app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import torch.nn.functional as F
+
+# Load the Hugging Face model and tokenizer for text classification
+model_name = "vai0511/ai-content-classifier"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Function to classify text (Synchronous Function)
+def classify_text(text: str):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():  # Disable gradient calculations for inference
+        outputs = model(**inputs)
+    
+    logits = outputs.logits  # Raw model predictions (logits)
+    probabilities = F.softmax(logits, dim=1)  # Convert logits to probabilities using softmax
+    percentages = probabilities[0].tolist()  # Convert probabilities to a list for easy access
+    labels = {0: "Human-Written", 1: "AI-Generated", 2: "Paraphrased"}
+    predicted_class = torch.argmax(logits, dim=1).item()
+    result = labels[predicted_class]
+    percentages = {labels[i]: round(percentages[i] * 100, 2) for i in range(len(percentages))}
+    return result, percentages
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=classify_text,
+    inputs=gr.Textbox(label="Enter Text to Classify"),
+    outputs=[gr.Textbox(label="Classification Result"), gr.JSON(label="Classification Percentages")],
+    live=True
+)
+
+# Launch Gradio interface
+iface.launch()