Update app.py

app.py

@@ -8,7 +8,7 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     max_seq_length = 2048,
     dtype = torch.float16,
     load_in_4bit = True,
-)
+).to("cpu")
 FastLanguageModel.for_inference(model) 
 
 def predict(input_text):
@@ -20,7 +20,7 @@ def predict(input_text):
         tokenize=True,
         add_generation_prompt=True,  
         return_tensors="pt",
-    )  
+    ).to("cpu") 
 
     outputs = model.generate(
         input_ids=inputs,