Update app.py

app.py

@@ -1,70 +1,144 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+# ============================================
+# KTH ID2223 Lab 2 - Llama 3.2 ChatBot
+# ============================================
+# 使用你的微调模型（safetensors 格式）
+MODEL_ID = "Marcus719/Llama-3.2-3B-Instruct-Lab2"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+client = InferenceClient(model=MODEL_ID)
 
+def chat(message, history, system_message, max_tokens, temperature, top_p):
+    """Generate response using HuggingFace Inference API"""
+    
     messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+    
+    # Add conversation history
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    
+    # Add current message
     messages.append({"role": "user", "content": message})
-
+    
+    # Stream response
     response = ""
-
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+        if chunk.choices and chunk.choices[0].delta.content:
+            token = chunk.choices[0].delta.content
+            response += token
+            yield response
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# ============================================
+# Gradio 界面
+# ============================================
+DEFAULT_SYSTEM_PROMPT = "You are a helpful, respectful and honest assistant."
 
+with gr.Blocks(theme=gr.themes.Soft(), title="🦙 Llama 3.2 ChatBot") as demo:
+    
+    gr.Markdown(
+        """
+        # 🦙 Llama 3.2 3B Instruct ChatBot
+        
+        **KTH ID2223 Scalable Machine Learning - Lab 2**
+        
+        This demo uses the Llama 3.2 3B Instruct model via HuggingFace Inference API.
+        
+        📦 Fine-tuned Model (GGUF): [Marcus719/Llama-3.2-3B-Instruct-FineTome-Lab2-GGUF](https://huggingface.co/Marcus719/Llama-3.2-3B-Instruct-FineTome-Lab2-GGUF)
+        """
+    )
+    
+    chatbot = gr.Chatbot(label="Chat", height=450, show_copy_button=True)
+    
+    with gr.Row():
+        msg = gr.Textbox(
+            placeholder="Type your message here...",
+            scale=4,
+            container=False,
+            autofocus=True
+        )
+        submit_btn = gr.Button("Send 🚀", scale=1, variant="primary")
+    
+    with gr.Accordion("⚙️ Settings", open=False):
+        system_prompt = gr.Textbox(
+            label="System Prompt",
+            value=DEFAULT_SYSTEM_PROMPT,
+            lines=2
+        )
+        with gr.Row():
+            max_tokens = gr.Slider(64, 1024, value=512, step=32, label="Max Tokens")
+            temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
+            top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
+    
+    with gr.Row():
+        clear_btn = gr.Button("🗑️ Clear Chat")
+        retry_btn = gr.Button("🔄 Regenerate")
+    
+    gr.Examples(
+        examples=[
+            "Hello! Can you introduce yourself?",
+            "Explain machine learning in simple terms.",
+            "What is the difference between fine-tuning and pre-training?",
+            "Write a short poem about AI.",
+        ],
+        inputs=msg,
+        label="💡 Try these examples"
+    )
+    
+    # Event handlers
+    def user_input(message, history):
+        return "", history + [[message, None]]
+    
+    def bot_response(history, system_prompt, max_tokens, temperature, top_p):
+        if not history:
+            return history
+        message = history[-1][0]
+        history_for_model = history[:-1]
+        for response in chat(message, history_for_model, system_prompt, max_tokens, temperature, top_p):
+            history[-1][1] = response
+            yield history
+    
+    def retry_last(history, system_prompt, max_tokens, temperature, top_p):
+        if history:
+            history[-1][1] = None
+            message = history[-1][0]
+            history_for_model = history[:-1]
+            for response in chat(message, history_for_model, system_prompt, max_tokens, temperature, top_p):
+                history[-1][1] = response
+                yield history
+    
+    msg.submit(user_input, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot_response, [chatbot, system_prompt, max_tokens, temperature, top_p], chatbot
+    )
+    submit_btn.click(user_input, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot_response, [chatbot, system_prompt, max_tokens, temperature, top_p], chatbot
+    )
+    clear_btn.click(lambda: [], None, chatbot, queue=False)
+    retry_btn.click(retry_last, [chatbot, system_prompt, max_tokens, temperature, top_p], chatbot)
+    
+    gr.Markdown(
+        """
+        ---
+        ### 📝 About This Project
+        
+        **Fine-tuning Details:**
+        - Base Model: `meta-llama/Llama-3.2-3B-Instruct`
+        - Dataset: [FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k)
+        - Method: QLoRA (4-bit quantization + LoRA)
+        - Framework: [Unsloth](https://github.com/unslothai/unsloth)
+        
+        Built with ❤️ for KTH ID2223 Lab 2
+        """
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()