Update app.py

app.py

@@ -42,10 +42,6 @@ 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):
@@ -72,7 +68,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         max_new_tokens=max_new_tokens, 
         do_sample=True, 
         temperature=temperature,
-        #eos_token_id = [151645, 151643],
+        eos_token_id = [128001, 128009],
     )
     
     thread = Thread(target=model.generate, kwargs=generate_kwargs)
@@ -109,7 +105,7 @@ with gr.Blocks(css=CSS) as demo:
                 minimum=128,
                 maximum=4096,
                 step=1,
-                value=256,
+                value=1024,
                 label="Max new tokens",
                 render=False,
             ),