update app

app.py

@@ -19,6 +19,7 @@ r_model = T5ForMultimodalGeneration.from_pretrained(rationale_model_dir, patch_s
 
 def inference_chat(input_image,input_text):
     with torch.no_grad():
+        print(input_image)
         img = Image.open(input_image).convert("RGB")
         input = transform(img).unsqueeze(0)
         out = vit_model.forward_features(input)

requirements.txt

@@ -1,5 +1,6 @@
+huggingface-hub>=0.4.0
 git+https://github.com/huggingface/transformers.git
 torch
 torchvision
 sentencepiece
-numpy
+numpy