Update app.py

app.py

@@ -1,407 +1,31 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-import time
-
-# Initialize the model and tokenizer
-@torch.no_grad()
-def load_model():
-    print("Loading Qwen3-0.6B model...")
-    
-    try:
-        # Load tokenizer and model
-        tokenizer = AutoTokenizer.from_pretrained(
-            "Qwen/Qwen3-0.6B",
-            trust_remote_code=True
-        )
-        
-        model = AutoModelForCausalLM.from_pretrained(
-            "Qwen/Qwen3-0.6B",
-            torch_dtype=torch.float16,
-            device_map="auto",
-            trust_remote_code=True
-        )
-        
-        print("Model loaded successfully!")
-        return tokenizer, model
-        
-    except Exception as e:
-        print(f"Error loading model: {e}")
-        # Fallback to a smaller model if Qwen fails
-        print("Trying fallback model...")
-        tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
-        model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
-        return tokenizer, model
-
-# Load the model
-tokenizer, model = load_model()
-
-def format_messages(history, new_message):
-    """
-    Format chat history and new message into the required format
-    """
-    messages = []
-    
-    # Add history
-    for human_msg, assistant_msg in history:
-        messages.extend([
-            {"role": "user", "content": human_msg},
-            {"role": "assistant", "content": assistant_msg}
-        ])
-    
-    # Add new message
-    messages.append({"role": "user", "content": new_message})
-    
-    return messages
-
-def generate_response(message, history, temperature=0.7, max_length=512):
-    """
-    Generate a response using the model
-    """
-    if tokenizer is None or model is None:
-        return "Model is not loaded properly. Please check the logs."
-    
-    try:
-        # Format messages
-        messages = format_messages(history, message)
-        
-        # Apply chat template
-        text = tokenizer.apply_chat_template(
-            messages,
-            tokenize=False,
-            add_generation_prompt=True
-        )
-        
-        # Tokenize
-        model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
-        
-        # Generate response
-        with torch.no_grad():
-            generated_ids = model.generate(
-                **model_inputs,
-                max_new_tokens=max_length,
-                temperature=temperature,
-                do_sample=True if temperature > 0.1 else False,
-                top_p=0.9,
-                repetition_penalty=1.1,
-                eos_token_id=tokenizer.eos_token_id,
-                pad_token_id=tokenizer.eos_token_id
-            )
-        
-        # Decode response
-        generated_ids = [
-            output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-        ]
-        
-        response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-        
-        # Clean up response
-        response = response.strip()
-        if "<|im_end|>" in response:
-            response = response.split("<|im_end|>")[0].strip()
-        
-        return response
-        
-    except Exception as e:
-        return f"Sorry, I encountered an error: {str(e)}"
-
-def chat_interface(message, history, temperature, max_length):
-    """
-    Main chat interface function
-    """
+import random
+
+# Simple fallback responses
+fallback_responses = [
+    "I understand you want me to explain quantum computing. It's a complex topic that deals with how very small particles behave differently from objects in our everyday world.",
+    "Quantum computing uses quantum bits or qubits, which can exist in multiple states at once, unlike regular computer bits that are only 0 or 1.",
+    "This allows quantum computers to solve certain problems much faster than traditional computers.",
+    "I'd be happy to help you learn about quantum computing! It's a fascinating field of physics and computer science.",
+    "Quantum computers use phenomena like superposition and entanglement to perform calculations in new ways."
+]
+
+def simple_chat(message, history):
     if not message.strip():
         return "", history
     
-    # Generate response
-    bot_response = generate_response(message, history, temperature, max_length)
+    # Simulate AI thinking
+    response = random.choice(fallback_responses)
     
     # Update history
-    history.append([message, bot_response])
+    new_history = history + [[message, response]]
     
-    return "", history
-
-def clear_chat():
-    """
-    Clear the chat history
-    """
-    return []
-
-def retry_last_response(history, temperature, max_length):
-    """
-    Retry the last user message
-    """
-    if not history:
-        return history
-    
-    # Remove the last assistant response
-    last_conversation = history[:-1]
-    last_user_message = history[-1][0]
-    
-    # Regenerate response
-    bot_response = generate_response(last_user_message, last_conversation, temperature, max_length)
-    
-    # Update history
-    last_conversation.append([last_user_message, bot_response])
-    
-    return last_conversation
-
-# Custom CSS for beautiful styling with better layout
-custom_css = """
-.gradio-container {
-    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
-}
-
-.main-container {
-    max-width: 1200px !important;
-    margin: 0 auto !important;
-    padding: 20px !important;
-}
-
-.chat-column {
-    min-height: 600px;
-}
-
-.control-column {
-    background: #f8f9fa;
-    border-radius: 15px;
-    padding: 20px;
-    height: fit-content;
-    position: sticky;
-    top: 20px;
-}
+    return "", new_history
 
-.chatbot-container {
-    border: 2px solid #e1e5e9;
-    border-radius: 15px;
-    padding: 0;
-    overflow: hidden;
-    background: white;
-    box-shadow: 0 4px 12px rgba(0,0,0,0.1);
-}
-
-#chatbot {
-    min-height: 500px;
-    max-height: 500px;
-    border: none !important;
-    background: white !important;
-    padding: 20px !important;
-}
-
-.input-container {
-    background: white;
-    padding: 20px;
-    border-top: 1px solid #e1e5e9;
-}
-
-.control-panel {
-    background: white;
-    padding: 20px;
-    border-radius: 10px;
-    margin-bottom: 20px;
-    box-shadow: 0 2px 8px rgba(0,0,0,0.1);
-}
-
-.model-info-card {
-    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-    color: white;
-    padding: 20px;
-    border-radius: 10px;
-    margin-top: 20px;
-}
-
-.gr-button {
-    background: linear-gradient(45deg, #667eea, #764ba2) !important;
-    border: none !important;
-    color: white !important;
-    border-radius: 10px !important;
-    padding: 10px 20px !important;
-    font-weight: 600 !important;
-    margin: 5px !important;
-}
-
-.gr-button:hover {
-    transform: translateY(-2px);
-    box-shadow: 0 5px 15px rgba(102, 126, 234, 0.4);
-}
-
-.clear-btn {
-    background: linear-gradient(45deg, #ff6b6b, #ee5a24) !important;
-}
-
-.retry-btn {
-    background: linear-gradient(45deg, #00b894, #00a085) !important;
-}
-
-.textbox {
-    border-radius: 10px !important;
-    border: 2px solid #e1e5e9 !important;
-    padding: 15px !important;
-}
-
-.textbox:focus {
-    border-color: #667eea !important;
-    box-shadow: 0 0 0 3px rgba(102, 126, 234, 0.1) !important;
-}
-
-.slider-container {
-    margin: 15px 0;
-}
-
-.examples-panel {
-    background: white;
-    padding: 15px;
-    border-radius: 10px;
-    margin-top: 20px;
-    border: 1px solid #e1e5e9;
-}
-
-.header {
-    text-align: center;
-    margin-bottom: 30px !important;
-}
-
-.header h1 {
-    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-    -webkit-background-clip: text;
-    -webkit-text-fill-color: transparent;
-    background-clip: text;
-    font-size: 2.5em !important;
-    margin-bottom: 10px !important;
-}
-
-.header p {
-    color: #666;
-    font-size: 1.2em;
-    margin: 0 !important;
-}
-"""
-
-# Create the Gradio interface with better layout
-with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
-    
-    with gr.Column(elem_classes="main-container"):
-        # Header
-        with gr.Column(elem_classes="header"):
-            gr.Markdown("# 🤖 Qwen3-0.6B Chatbot")
-            gr.Markdown("Chat with Alibaba's advanced Qwen3-0.6B model! Experience fluent and intelligent conversations.")
-        
-        with gr.Row(equal_height=False):
-            # Left Column - Chat Interface (Larger)
-            with gr.Column(scale=3, elem_classes="chat-column"):
-                with gr.Column(elem_classes="chatbot-container"):
-                    chatbot = gr.Chatbot(
-                        value=[["Hello! How can I help you today?", ""]],
-                        label="💬 Chat with Qwen3",
-                        elem_id="chatbot",
-                        show_copy_button=True,
-                        avatar_images=("👤", "🤖"),
-                        height=500,
-                        show_label=True,
-                        container=True
-                    )
-                
-                with gr.Column(elem_classes="input-container"):
-                    with gr.Row():
-                        msg = gr.Textbox(
-                            label="",
-                            placeholder="Type your message here...",
-                            lines=2,
-                            scale=4,
-                            container=False,
-                            show_label=False
-                        )
-                        with gr.Column(scale=1):
-                            submit_btn = gr.Button("Send 🚀", size="lg")
-                    
-                    with gr.Row():
-                        clear_btn = gr.Button("🗑️ Clear Chat", elem_classes="clear-btn")
-                        retry_btn = gr.Button("🔄 Retry Last", elem_classes="retry-btn")
-                        gr.HTML("""<div style="flex: 1; text-align: center; color: #666; font-size: 12px; padding: 10px;">
-                            💡 Tip: Press Enter to send, Shift+Enter for new line
-                        </div>""")
-            
-            # Right Column - Controls (Smaller)
-            with gr.Column(scale=1, elem_classes="control-column"):
-                with gr.Column(elem_classes="control-panel"):
-                    gr.Markdown("### ⚙️ Generation Settings")
-                    
-                    temperature = gr.Slider(
-                        minimum=0.1,
-                        maximum=1.5,
-                        value=0.7,
-                        step=0.1,
-                        label="Temperature",
-                        info="Controls creativity: lower = more focused, higher = more creative"
-                    )
-                    
-                    max_length = gr.Slider(
-                        minimum=64,
-                        maximum=1024,
-                        value=256,
-                        step=64,
-                        label="Max Response Length",
-                        info="Maximum tokens in generated response"
-                    )
-                
-                with gr.Column(elem_classes="model-info-card"):
-                    gr.Markdown("### ℹ️ About This Model")
-                    gr.Markdown("""
-                    **Model:** Qwen3-0.6B  
-                    **Provider:** Alibaba Group  
-                    **Context:** 128K tokens  
-                    **Languages:** Multilingual  
-                    
-                    ✨ **Capabilities:**
-                    - Natural conversations
-                    - Creative writing
-                    - Problem solving
-                    - Code generation
-                    """)
-        
-        # Examples Section
-        with gr.Column(elem_classes="examples-panel"):
-            gr.Markdown("### 💡 Try These Examples")
-            gr.Examples(
-                examples=[
-                    "Explain quantum computing in simple terms",
-                    "Write a short poem about artificial intelligence",
-                    "What are the benefits of renewable energy?",
-                    "How do I learn programming effectively?",
-                    "Tell me an interesting fact about space exploration",
-                    "Help me plan a healthy weekly meal plan"
-                ],
-                inputs=msg,
-                label="Click any example to start chatting!",
-                examples_per_page=6
-            )
-    
-    # Event handlers
-    submit_event = msg.submit(
-        chat_interface,
-        inputs=[msg, chatbot, temperature, max_length],
-        outputs=[msg, chatbot]
-    )
-    
-    submit_btn.click(
-        chat_interface,
-        inputs=[msg, chatbot, temperature, max_length],
-        outputs=[msg, chatbot]
-    )
-    
-    clear_btn.click(
-        clear_chat,
-        outputs=[chatbot]
-    )
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(label="Your message")
     
-    retry_btn.click(
-        retry_last_response,
-        inputs=[chatbot, temperature, max_length],
-        outputs=[chatbot]
-    )
+    msg.submit(simple_chat, [msg, chatbot], [msg, chatbot])
 
-if __name__ == "__main__":
-    demo.launch(
-        server_name="0.0.0.0",
-        share=False,
-        show_error=True
-    )
+demo.launch()