Update app.py

app.py

@@ -12,6 +12,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 
 
 
+
 zero = torch.Tensor([0]).cuda()
 print(zero.device) # <-- 'cpu' 🤔
 @spaces.GPU
@@ -21,7 +22,9 @@ def greet(n):
 
 print(zero.device) # <-- 'cuda:0' 🤗
 
-device = "cpu"  # CPU kullanıyoruz
+
+demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
+demo.launch()
 torch_dtype = torch.float32  # float32 seçtik çünkü CPU'da bf16 genelde yok
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch_dtype)