Update app.py

app.py

@@ -68,7 +68,7 @@ def generate_prompt(instruction, input=None):
     else:
         return PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
 
-@spaces.GPU
+
 def getIds(inputs):
     return inputs["input_ids"].cuda()
 
@@ -83,7 +83,8 @@ def generator(input_ids, generation_config, max_new_tokens):
                 max_new_tokens=max_new_tokens,
             )
     return generation_output
-    
+
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -94,7 +95,7 @@ def respond(
 ):
     ins_f = generate_prompt(message,None)
     inputs  =  tokenizer(ins_f, return_tensors="pt")
-    input_ids = getIds(inputs)
+    input_ids = inputs["input_ids"].cuda()
     max_new_tokens = 512
     generation_config = GenerationConfig(
             temperature=0.1,
@@ -155,4 +156,4 @@ demo = gr.ChatInterface(
 )
 if __name__ == "__main__":
     model.eval()
-    demo.launch(share=True)
+    demo.launch()