Update app.py

app.py

@@ -1,40 +1,14 @@
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 from datasets import load_dataset
-import os
-
-MODEL = "yagnik12/AI_Text_Detecter_HanxiGuo_BiScope-Data"
-
-tokenizer = AutoTokenizer.from_pretrained(MODEL, use_auth_token=os.getenv("HF_TOKEN"))
-model = AutoModelForSequenceClassification.from_pretrained(MODEL, use_auth_token=os.getenv("HF_TOKEN"))
-
-detector = pipeline("text-classification", model=model, tokenizer=tokenizer, return_all_scores=True)
-
-# Load BiScope test samples
-biscope = load_dataset("HanxiGuo/BiScope_Data", split="test[:20]")
-
-def detect_ai(text):
-    results = detector(text)[0]
-    human_score = [r["score"] for r in results if r["label"] in ["LABEL_0", "0"]][0]
-    ai_score = [r["score"] for r in results if r["label"] in ["LABEL_1", "1"]][0]
-    prediction = "🧑 Human" if human_score > ai_score else "🤖 AI"
-    return {
-        "Prediction": prediction,
-        "Human Probability": round(human_score * 100, 2),
-        "AI Probability": round(ai_score * 100, 2),
-    }
-
-with gr.Blocks() as demo:
-    gr.Markdown("# AI vs Human Text Detector (BiScope Dataset)")
+import gradio as gr
 
-    with gr.Row():
-        inp = gr.Textbox(lines=5, placeholder="Enter text here...")
-        out = gr.JSON()
-    btn = gr.Button("Detect")
-    btn.click(fn=detect_ai, inputs=inp, outputs=out)
+# Load MAGE dataset
+dataset = load_dataset("yaful/MAGE")
 
-    gr.Markdown("### 🔎 Try BiScope Dataset Examples")
-    examples = [biscope[i]["text"] for i in range(len(biscope))]
-    gr.Examples(examples=examples, inputs=inp)
+# Simple function to display a sample
+def show_sample(index):
+    sample = dataset['train'][index]
+    return f"Text: {sample['text']}\nLabel: {sample['label']}"
 
+# Create Gradio interface
+demo = gr.Interface(fn=show_sample, inputs=gr.Number(label="Sample Index"), outputs="text")
 demo.launch()