Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+
+ml_questions = [
+    "Explain the bias–variance tradeoff.",
+    "What is regularization and why is it useful?",
+    "How does gradient descent work?",
+    "What is the difference between batch, mini‑batch, and stochastic gradient descent?",
+    "Explain precision, recall, F1 score, and when you would use each.",
+    "What is overfitting and how do you prevent it?",
+    "Describe how a decision tree works.",
+    "What is the difference between bagging and boosting?",
+    "Explain how a convolutional neural network processes images.",
+    "What is the purpose of a learning rate scheduler?",
+    "How does dropout work and why is it effective?",
+    "What is the difference between L1 and L2 regularization?",
+    "Explain the concept of embeddings.",
+    "What is transfer learning and when is it useful?",
+    "How do you evaluate a clustering algorithm?",
+    "What is the difference between generative and discriminative models?",
+    "Explain the attention mechanism in transformers.",
+    "What is gradient vanishing/exploding and how do you address it?",
+    "Describe the steps in a typical ML pipeline.",
+    "What is the difference between supervised, unsupervised, and reinforcement learning?"
+]
+
+def get_questions(n):
+    n = int(n)
+    return "\n\n".join(ml_questions[:n])
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🧠 ML Interview Question Generator\nSelect how many questions you want to display.")
+    
+    num = gr.Slider(1, len(ml_questions), value=5, step=1, label="Number of Questions")
+    output = gr.Textbox(label="Interview Questions", lines=20)
+    
+    num.change(fn=get_questions, inputs=num, outputs=output)
+
+demo.launch()