fixed the device problem

app.py

@@ -203,6 +203,7 @@ class InferenceRunner:
     @torch.no_grad()
     def predict(self, rxn_dict, temperature=1):
         graphs, prompt_tokens = self.tokenize(rxn_dict)
+        self.model.blip2opt = self.model.blip2opt.to('cuda')
         result_dict = rxn_dict
         samples = {'graphs': graphs, 'prompt_tokens': prompt_tokens}
         prediction = self.model.blip2opt.generate(