Update app.py

app.py

@@ -42,6 +42,10 @@ model = AutoModelForCausalLM.from_pretrained(
           device_map="auto",
         )
 tokenizer = AutoTokenizer.from_pretrained(MODELS)
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):