Update app.py

app.py

@@ -25,10 +25,6 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
     torch_dtype=torch.bfloat16,
 )
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
 model.config.sliding_window = 4096
 model.eval()
 
@@ -63,7 +59,6 @@ def generate(
         temperature=temperature,
         num_beams=1,
         repetition_penalty=repetition_penalty,
-        eos_token_id=terminators,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()