Update app.py

app.py

@@ -81,24 +81,6 @@ def respond(
             prompt += f"{role}{hmessage['content']}\n<|end|>"        
         prompt += f"<|assistant|>"
 
-        """
-        # Generate the response
-        response_output = generator(
-            prompt,
-            generation_config=generator_conf,
-            max_new_tokens=max_tokens,
-            do_sample=True,
-            top_p=top_p,
-            repetition_penalty=1.2,
-            temperature=temperature
-        )
-    
-        generated_text = response_output[0]['generated_text']
-    
-        # Extract the assistant's response
-        result = generated_text[len(prompt):]
-        # result = prompt +':'+result
-        """
         tokens_cnt = 0
         tokens_inc = 3
         last_token_len = 1
@@ -135,7 +117,7 @@ status_text = \
   f"Current CPU usage is {cpu_usage:.2f}% .'" + \
   f"You may ask questions such as 'What is biology?' or 'What is the human body?'"
 
-"""
+# """
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -172,7 +154,7 @@ with gr.Blocks() as demo:
             ),
         ],
     )
-
+"""
 
 if __name__ == "__main__":
     demo.launch()