diff --git a/examples/offline_inference_npu.py b/examples/offline_inference_npu_v0.py
similarity index 94%
rename from examples/offline_inference_npu.py
rename to examples/offline_inference_npu_v0.py
index 76d00d2..b6a1156 100644
--- a/examples/offline_inference_npu.py
+++ b/examples/offline_inference_npu_v0.py
@@ -17,6 +17,11 @@
 # Adapted from vllm-project/vllm/examples/offline_inference/basic.py
 #
 
+import os
+
+os.environ["VLLM_USE_V1"] = "0"
+os.environ["VLLM_USE_MODELSCOPE"] = "True"
+
 from vllm import LLM, SamplingParams
 
 prompts = [
diff --git a/examples/offline_inference_npu_v1.py b/examples/offline_inference_npu_v1.py
index 939d84b..72486f0 100644
--- a/examples/offline_inference_npu_v1.py
+++ b/examples/offline_inference_npu_v1.py
@@ -19,10 +19,11 @@
 
 import os
 
+os.environ["VLLM_USE_MODELSCOPE"] = "True"
+os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
+
 from vllm import LLM, SamplingParams
 
-os.environ["VLLM_USE_V1"] = "1"
-os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 
 if __name__ == "__main__":
     prompts = [
@@ -35,7 +36,7 @@ if __name__ == "__main__":
     # Create a sampling params object.
     sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
     # Create an LLM.
-    llm = LLM(model="/data/weights/deepseek-ai/deepseekv3-lite-base-latest",
+    llm = LLM(model="deepseek-ai/DeepSeek-V2-Lite",
               tensor_parallel_size=2,
               enforce_eager=True,
               trust_remote_code=True,