Update app.py

app.py

@@ -43,8 +43,8 @@ def setup_model():
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     model = AutoModelForSeq2SeqLM.from_pretrained(
         model_id,
-        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-        low_cpu_mem_usage=True
+        # Removed low_cpu_mem_usage parameter
+        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
     )
     
     if torch.cuda.is_available():