Update app.py

app.py

@@ -1,9 +1,27 @@
 import gradio as gr
 import spaces
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", device_map="auto")
+
 
 @spaces.GPU 
-def greet(name, intensity):
-    return "Hello, " + name + "!" * int(intensity)
+def greet(content, intensity):
+    messages = [
+        {"role": "user", "content": content},
+    ]
+    inputs = tokenizer.apply_chat_template(
+    	messages,
+    	add_generation_prompt=True,
+    	tokenize=True,
+    	return_dict=True,
+    	return_tensors="pt",
+    ).to(model.device)
+    
+    outputs = model.generate(**inputs, max_new_tokens=40)
+    
+    return tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])
 
 demo = gr.Interface(
     fn=greet,