jhghj

app.py

@@ -48,7 +48,7 @@ def model_inference(
     model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-2B-Instruct",attn_implementation="flash_attention_2", trust_remote_code=True, torch_dtype="auto").cuda().eval()
 
     # default processer
-    processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
+    processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-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 count range of 256-1280, to balance speed and memory usage.
     # min_pixels = 256*28*28