Update app.py

app.py

@@ -36,7 +36,6 @@ h1 {
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
-   
 
 
 def extract_text(path):
@@ -99,18 +98,14 @@ def mode_load(path):
 
 @spaces.GPU()
 def stream_chat(message, history: list, temperature: float, max_length: int, top_p: float, top_k: int, penalty: float):
-   
-   if history.len()==0:
-       model = AutoModelForCausalLM.from_pretrained(
+    if history.len()==0:
+        model = AutoModelForCausalLM.from_pretrained(
             MODEL_ID,
             torch_dtype=torch.bfloat16,
             low_cpu_mem_usage=True,
             trust_remote_code=True
-       )
+        )
         
-     
-        
-    
     print(f'message is - {message}')
     print(f'history is - {history}')
     conversation = []
@@ -250,5 +245,5 @@ with gr.Blocks(css=CSS, theme="soft", fill_height=True) as demo:
     ),
     gr.Examples(EXAMPLES, [chat_input])
 
-
-demo.queue(api_open=False).launch(show_api=False, share=False, )#server_name="0.0.0.0", )
+if __name__ == "__main__":
+    demo.queue(api_open=False).launch(show_api=False, share=False, )#server_name="0.0.0.0", )