diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
index 351311b3283..aa5740d3da5 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
@@ -97,7 +97,7 @@ python llama.py --repo-id-or-model-path meta-llama/Meta-Llama-3-8B-Instruct
 python qwen2.py
 
 # to run Qwen2-7B-Instruct
-python qwen2.py  --repo-id-or-model-path Qwen/Qwen2-7B-Instruct --inter-pp 4
+python qwen2.py  --repo-id-or-model-path Qwen/Qwen2-7B-Instruct
 
 # to run MiniCPM-1B-sft-bf16
 python minicpm.py
diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/qwen2.py b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/qwen2.py
index fd0f1482147..2e4d195f80c 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/qwen2.py
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/qwen2.py
@@ -43,8 +43,8 @@
     parser.add_argument("--max-output-len", type=int, default=1024)
     parser.add_argument("--max-prompt-len", type=int, default=512)
     parser.add_argument("--disable-transpose-value-cache", action="store_true", default=False)
-    parser.add_argument("--intra-pp", type=int, default=2)
-    parser.add_argument("--inter-pp", type=int, default=1)
+    parser.add_argument("--intra-pp", type=int, default=None)
+    parser.add_argument("--inter-pp", type=int, default=None)
 
     args = parser.parse_args()
     model_path = args.repo_id_or_model_path