Update app.py

app.py

@@ -71,6 +71,7 @@ def start_generating(message):
     thread = Thread(target=model.generate,kwargs={"input_ids": inputs,
                              "streamer": streamer, "max_new_tokens": 500}) 
     thread.start() # now start the thread
+    thread.join()
 
 
 # for new_text in streamer:
@@ -92,7 +93,7 @@ def echo(message, history):
     if chunk is not None:
           temp += chunk + ""
     yield temp
-  thread.join()
+  #thread.join()
 # username = os.getenv('username')
 # password = os.getenv('pass')
 demo = gr.ChatInterface(fn=echo, examples=["hello", "hi"], title="llama-3 finetuned")