Update README.md

README.md

@@ -96,22 +96,25 @@ 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-AWQ")
 
 # default: Load the model on the available device(s)
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2.5-VL-7B-Instruct-AWQ", 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.
 # model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-#     "Qwen/Qwen2.5-VL-7B-Instruct-AWQ",
+#     model_dir,
 #     torch_dtype=torch.bfloat16,
 #     attn_implementation="flash_attention_2",
 #     device_map="auto",
 # )
 
 # default processer
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct-AWQ")
+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.
@@ -207,7 +210,7 @@ The model supports a wide range of resolution inputs. By default, it uses the na
 min_pixels = 256 * 28 * 28
 max_pixels = 1280 * 28 * 28
 processor = AutoProcessor.from_pretrained(
-    "Qwen/Qwen2.5-VL-7B-Instruct-AWQ", min_pixels=min_pixels, max_pixels=max_pixels
+    model_dir, min_pixels=min_pixels, max_pixels=max_pixels
 )
 ```