Fixes

app.py

@@ -6,7 +6,7 @@ from transformers import Blip2Processor, Blip2ForConditionalGeneration
 
 processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
 model = Blip2ForConditionalGeneration.from_pretrained(
-    "Salesforce/blip2-opt-2.7b", device_map={"": 0}, torch_dtype=torch.float16
+    "Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16
 )
 
 
@@ -16,7 +16,7 @@ picture = st.camera_input("Take a picture", disabled=not enable)
 if picture:
 	image = Image.open(picture)
 	prompt = "Question: At what location is this person most likely attending this online meeting? Answer:"
-	inputs = processor(images=image, text=prompt, return_tensors="pt").to(device="cuda", dtype=torch.float16)
+	inputs = processor(images=image, text=prompt, return_tensors="pt")
 
 	generated_ids = model.generate(**inputs)
 	generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()

conda

@@ -0,0 +1,4 @@
+Pillow
+transformers
+torch
+accelerate