Update app.py

app.py

@@ -15,7 +15,7 @@ from io import BytesIO
 
 from PIL import Image as PILIMAGE
 
-from transformers import CLIPProcessor, CLIPModel, CLIPTokenizer
+from transformers import CLIPProcessor, CLIPModel, CLIPTokenizer, CLIPConfig
 from sentence_transformers import SentenceTransformer, util
 
 
@@ -23,6 +23,7 @@ from sentence_transformers import SentenceTransformer, util
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Define model
+config = CLIPConfig.from_pretrained("openai/clip-vit-base-patch32")
 model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32", config=config.vision_config).to(device)
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")