diff --git a/README.md b/README.md
index 9c9f73a..303ed4e 100644
--- a/README.md
+++ b/README.md
@@ -104,7 +104,7 @@ We have three models with 3, 7 and 72 billion parameters. This repo contains the
 ## Requirements
 The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
 ```
-pip install git+https://github.com/huggingface/transformer accelerate
+pip install git+https://github.com/huggingface/transformers accelerate
 ```
 or you might encounter the following error:
 ```
@@ -118,7 +118,7 @@ Below, we provide simple examples to show how to use Qwen2.5-VL with 🤖 ModelS
 
 The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
 ```
-pip install git+https://github.com/huggingface/transformer accelerate
+pip install git+https://github.com/huggingface/transformers accelerate
 ```
 or you might encounter the following error:
 ```
@@ -142,10 +142,13 @@ 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(
-    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
+    model_dir, 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.
@@ -157,7 +160,7 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 # )
 
 # default processer
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
+processor = AutoProcessor.from_pretrained(model_dir)
 
 # 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.