Create app.py

app.py

@@ -0,0 +1,5 @@
+# Load model directly
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+model = AutoModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")