Fix indentation - clean app.py for Qwen3.5 AWQ ZeroGPU chat

app.py

@@ -11,45 +11,46 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
 print("Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
-        MODEL_ID,
-        torch_dtype=torch.float16,
-        device_map="cpu",
-        trust_remote_code=True,
+    MODEL_ID,
+    torch_dtype=torch.float16,
+    device_map="cpu",
+    trust_remote_code=True,
 )
 model.eval()
 print("Model loaded.")
 
+
 @spaces.GPU(duration=120)
 def respond(message, history, system_message, max_new_tokens, temperature, top_p, enable_thinking):
-        model.to("cuda")
-
-        messages = [{"role": "system", "content": system_message}]
-        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})
-                            messages.append({"role": "user", "content": message})
-
-                text = tokenizer.apply_chat_template(
-                            messages,
-                            tokenize=False,
-                            add_generation_prompt=True,
-                            chat_template_kwargs={"enable_thinking": enable_thinking},
-                )
+    model.to("cuda")
+
+    messages = [{"role": "system", "content": system_message}]
+    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})
+    messages.append({"role": "user", "content": message})
+
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+        chat_template_kwargs={"enable_thinking": enable_thinking},
+    )
     inputs = tokenizer([text], return_tensors="pt").to("cuda")
 
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
     generation_kwargs = dict(
-                **inputs,
-                streamer=streamer,
-                max_new_tokens=max_new_tokens,
-                temperature=temperature,
-                top_p=top_p,
-                top_k=20,
-                do_sample=True,
-                repetition_penalty=1.1,
+        **inputs,
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        top_k=20,
+        do_sample=True,
+        repetition_penalty=1.1,
     )
 
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
@@ -60,74 +61,71 @@ def respond(message, history, system_message, max_new_tokens, temperature, top_p
     display_text = ""
 
     for new_text in streamer:
-                partial += new_text
-                if enable_thinking:
-                                if "</think>" in partial and not thinking_done:
-                                                    thinking_done = True
-                                                    parts = partial.split("</think>", 1)
-                                                    display_text = parts[1].lstrip("\n")
-                                elif thinking_done:
-                                                    display_text = partial.split("</think>", 1)[1].lstrip("\n")
-                                else:
-                                                    display_text = ""
-                else:
-                                display_text = partial
-                            yield display_text
+        partial += new_text
+        if enable_thinking:
+            if "</think>" in partial and not thinking_done:
+                thinking_done = True
+                display_text = partial.split("</think>", 1)[1].lstrip("\n")
+            elif thinking_done:
+                display_text = partial.split("</think>", 1)[1].lstrip("\n")
+            else:
+                display_text = ""
+        else:
+            display_text = partial
+        yield display_text
 
     model.to("cpu")
     torch.cuda.empty_cache()
 
 
 with gr.Blocks(title="Qwen3.5-35B-A3B Chat") as demo:
-        gr.Markdown("# Qwen3.5-35B-A3B AWQ Chat\nPowered by ZeroGPU (H200) | 4-bit AWQ quantized | 25.5 GB")
+    gr.Markdown("# Qwen3.5-35B-A3B AWQ Chat\nPowered by ZeroGPU (H200) | 4-bit AWQ quantized | 25.5 GB")
 
     chatbot = gr.Chatbot(height=500, label="Qwen3.5-35B-A3B")
 
     with gr.Row():
-                msg = gr.Textbox(
-                    placeholder="Type your message here...",
-                    label="Your message",
-                    scale=4,
-    )
+        msg = gr.Textbox(
+            placeholder="Type your message here...",
+            label="Your message",
+            scale=4,
+        )
         send_btn = gr.Button("Send", variant="primary", scale=1)
 
     with gr.Accordion("Settings", open=False):
-                system_message = gr.Textbox(
-                    value="You are a helpful, smart, and concise AI assistant.",
-                    label="System message",
-    )
+        system_message = gr.Textbox(
+            value="You are a helpful, smart, and concise AI assistant.",
+            label="System message",
+        )
         enable_thinking = gr.Checkbox(value=True, label="Enable thinking mode (chain of thought)")
         max_new_tokens = gr.Slider(minimum=64, maximum=8192, value=2048, step=64, label="Max new tokens")
         temperature = gr.Slider(minimum=0.1, maximum=2.0, value=1.0, step=0.1, label="Temperature")
         top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
 
     def user_turn(user_message, history):
-                return "", history + [[user_message, None]]
-
-            def bot_turn(history, system_message, max_new_tokens, temperature, top_p, enable_thinking):
-                        user_message = history[-1][0]
-                        bot_history = history[:-1]
-                        response = ""
-                        for chunk in respond(user_message, bot_history, system_message, max_new_tokens, temperature, top_p, enable_thinking):
-                                        response = chunk
-                                        history[-1][1] = response
-                                        yield history
-
-                                msg.submit(user_turn, [msg, chatbot], [msg, chatbot]).then(
-                                            bot_turn, [chatbot, system_message, max_new_tokens, temperature, top_p, enable_thinking], chatbot
-                                )
+        return "", history + [[user_message, None]]
+
+    def bot_turn(history, system_message, max_new_tokens, temperature, top_p, enable_thinking):
+        user_message = history[-1][0]
+        bot_history = history[:-1]
+        for chunk in respond(user_message, bot_history, system_message, max_new_tokens, temperature, top_p, enable_thinking):
+            history[-1][1] = chunk
+            yield history
+
+    msg.submit(user_turn, [msg, chatbot], [msg, chatbot]).then(
+        bot_turn, [chatbot, system_message, max_new_tokens, temperature, top_p, enable_thinking], chatbot
+    )
     send_btn.click(user_turn, [msg, chatbot], [msg, chatbot]).then(
-                bot_turn, [chatbot, system_message, max_new_tokens, temperature, top_p, enable_thinking], chatbot
+        bot_turn, [chatbot, system_message, max_new_tokens, temperature, top_p, enable_thinking], chatbot
     )
 
     gr.Examples(
-                examples=[
-                                ["What is the square root of 144? Think step by step."],
-                                ["Write a Python function to check if a number is prime."],
-                                ["Explain quantum entanglement in simple terms."],
-                                ["Translate 'Hello, how are you?' into French, Spanish, and Japanese."],
-                ],
-                inputs=msg,
+        examples=[
+            ["What is the square root of 144? Think step by step."],
+            ["Write a Python function to check if a number is prime."],
+            ["Explain quantum entanglement in simple terms."],
+            ["Translate 'Hello, how are you?' into French, Spanish, and Japanese."],
+        ],
+        inputs=msg,
     )
 
 demo.launch()