Update app.py

resolve padding issue

app.py

@@ -81,7 +81,11 @@ quantization_config = BitsAndBytesConfig(
 )
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-model = AutoModelForCausalLM.from_pretrained(
+# Set the pad token to be the same as the end of sequence token
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+    tokenizer.pad_token_id = tokenizer.eos_token_id
+    model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
     quantization_config=quantization_config,