diff --git a/README.md b/README.md
index 29542c0..5f16903 100644
--- a/README.md
+++ b/README.md
@@ -7,8 +7,6 @@ pipeline_tag: image-text-to-text
 tags:
 - multimodal
 library_name: transformers
-base_model:
-- Qwen/Qwen2.5-VL-7B-Instruct
 ---
 
 # Qwen2.5-VL-7B-Instruct
@@ -142,13 +140,10 @@ Here we show a code snippet to show you how to use the chat model with `transfor
 ```python
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
 from qwen_vl_utils import process_vision_info
-from modelscope import snapshot_download
-
-model_dir=snapshot_download("Qwen/Qwen2.5-VL-7B-Instruct")
 
 # default: Load the model on the available device(s)
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    model_dir, torch_dtype="auto", device_map="auto"
+    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
 )
 
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
@@ -160,7 +155,7 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 # )
 
 # default processer
-processor = AutoProcessor.from_pretrained(model_dir)
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
 
 # The default range for the number of visual tokens per image in the model is 4-16384.
 # You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.