Update app.py

app.py

@@ -28,16 +28,15 @@ def predict(message, history):
         top_p=0.2,
         top_k=20,
         temperature=0.1,
+        repetition_penalty=2.0,
+        length_penalty=-0.5,
         num_beams=1
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()  # Starting the generation in a separate thread.
     partial_message = ""
     for new_token in streamer:
-        partial_message += new_token
-        if '</s>' in partial_message:  # Breaking the loop if the stop token is generated.
-            break
-        yield partial_message
+        yield new_token
 
 # Setting up the Gradio chat interface.
 gr.ChatInterface(predict,