hugvh

app.py

@@ -42,12 +42,7 @@ def model_inference(
     # )
 
     #We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
-    model = Qwen2VLForConditionalGeneration.from_pretrained(
-        "Qwen/Qwen2-VL-7B-Instruct",
-        torch_dtype=torch.bfloat16,
-       # attn_implementation="flash_attention_2",
-        device_map="auto",
-    )
+    model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", trust_remote_code=True, torch_dtype="auto").cuda().eval()
 
     # default processer
     processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")