Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import BlipProcessor, BlipForQuestionAnswering
 
 # Initialize the model and processor
 processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base")
-model = BlipForQuestionAnswering.from_pretrained("ManishThota/InstructBlip-VQA")
+model = BlipForQuestionAnswering.from_pretrained("ManishThota/InstructBlip-VQA").to("cuda")
 # model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
 
 def predict_answer(image, question):
@@ -13,7 +13,7 @@ def predict_answer(image, question):
     image = image.convert("RGB")
 
     # Prepare inputs
-    encoding = processor(image, question, return_tensors="pt")
+    encoding = processor(image, question, return_tensors="pt").to("cuda:0", torch.float16)
 
     out = model.generate(**encoding)
     generated_text = processor.decode(out[0], skip_special_tokens=True)