Update app.py

app.py

@@ -6,7 +6,10 @@ MODEL_ID = "Qwen/Qwen2.5-Coder-1.5B-Instruct"  # or your model
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.float16 if device=="cuda" else torch.float32)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID, 
+    torch_dtype=torch.float16 if device == "cuda" else torch.float32
+)
 model.to(device)
 
 def generate(prompt):
@@ -14,5 +17,10 @@ def generate(prompt):
     outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.2)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-demo = gr.Interface(fn=generate, inputs="text", outputs="text")
-demo.launch()
+demo = gr.Interface(
+    fn=generate,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
+    outputs=gr.Textbox(lines=2, max_lines=30)  # auto-expands up to 30 lines
+)
+
+demo.launch()