Update app.py

app.py

@@ -60,6 +60,7 @@ def chat(message, history, temperature, max_new_tokens):
     streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
     
     def generate():
+        stop_tokens = ["<|endoftext|>", "<|im_end|>","|im_end|"]
         nonlocal generated_tokens
         for response in model_pipeline(
             prompt,