Update app.py

app.py

@@ -39,7 +39,6 @@ class KeywordsStoppingCriteria(StoppingCriteria):
         self.tokenizer = tokenizer
         self.start_len = input_ids.shape[1]
         
-    @spaces.GPU
     def call_for_batch(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
         offset = min(output_ids.shape[1] - self.start_len, self.max_keyword_len)
         self.keyword_ids = [keyword_id.to(output_ids.device) for keyword_id in self.keyword_ids]
@@ -53,7 +52,6 @@ class KeywordsStoppingCriteria(StoppingCriteria):
                 return True
         return False
         
-    @spaces.GPU
     def __call__(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
         outputs = []
         for i in range(output_ids.shape[0]):