Update app.py

app.py

@@ -7,7 +7,7 @@ tokenizer = AutoTokenizer.from_pretrained("ping98k/typhoon-7b-rag-instruct-th")
 model = AutoModelForCausalLM.from_pretrained("ping98k/typhoon-7b-rag-instruct-th", device_map={"": 0})
 
 
-'''def response(instruction, history, inputText):
+def response(instruction, history, inputText):
     inp = f"""### Instruction:
 {instruction}
 
@@ -38,9 +38,9 @@ gr.ChatInterface(
     additional_inputs=[
         gr.Textbox(defaultInput, label="Input Text"),
     ],
-).launch()'''
+).launch()
 
-@spaces.GPU(duration=120)
+'''@spaces.GPU(duration=120)
 def response(inp):
     input_ids = tokenizer(inp, return_tensors='pt').to("cuda")
     beam_output = model.generate(**input_ids, max_new_tokens=300)
@@ -56,4 +56,4 @@ gradio_interface = gr.Interface(
   inputs = "text",
   outputs = "text"
 )
-gradio_interface.launch()
+gradio_interface.launch()'''