Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import spaces
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen3-4B-Instruct-2507"
+
+# Load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+@spaces.GPU(duration=120)
+def generate_response(prompt):
+    # Prepare the model input
+    messages = [
+        {"role": "user", "content": prompt}
+    ]
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+    # Conduct text completion
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=1024  # Reduced for performance and safety
+    )
+    output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+    content = tokenizer.decode(output_ids, skip_special_tokens=True)
+    return content
+
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Qwen Chatbot")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Input")
+    clear = gr.Button("Clear")
+
+    def respond(message, chat_history):
+        if not message:
+            return "", chat_history
+        
+        bot_response = generate_response(message)
+        chat_history.append((message, bot_response))
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+# Launch the app
+demo.launch()