Update app.py

app.py

@@ -56,8 +56,8 @@ model = AutoModelForCausalLM.from_pretrained(
     quantization_config=quantization_config).eval().to(device)
 
 # Ensure `pad_token_id` is set
-if tokenizer.pad_token_id is None:
-    tokenizer.pad_token_id = tokenizer.eos_token_id
+# if tokenizer.pad_token_id is None:
+#     tokenizer.pad_token_id = tokenizer.eos_token_id
 
 @spaces.GPU()
 def stream_chat(
@@ -91,8 +91,6 @@ def stream_chat(
         max_new_tokens = max_new_tokens,
         do_sample = False if temperature == 0 else True,
         top_p = top_p,
-        eos_token_id = tokenizer.eos_token_id,
-        pad_token_id = tokenizer.pad_token_id,
         temperature = temperature,
         streamer=streamer,
     )