Update app.py

app.py

@@ -5,15 +5,17 @@ import open_clip
 
 from huggingface_hub import hf_hub_download
 
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
 torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
 torch.hub.download_url_to_file('https://huggingface.co/datasets/nielsr/textcaps-sample/resolve/main/stop_sign.png', 'stop_sign.png')
 torch.hub.download_url_to_file('https://cdn.openai.com/dall-e-2/demos/text2im/astronaut/horse/photo/0.jpg', 'astronaut.jpg')
 
 git_processor_large_coco = AutoProcessor.from_pretrained("microsoft/git-large-coco")
-git_model_large_coco = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco", device_map="auto")
+git_model_large_coco = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco").to(device)
 
 blip_processor_large = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-blip_model_large = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", device_map="auto")
+blip_model_large = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to(device)
 
 blip2_processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-6.7b")
 blip2_model_4_bit = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-6.7b", device_map="auto", load_in_4bit=True, torch_dtype=torch.float16)
@@ -21,8 +23,6 @@ blip2_model_4_bit = Blip2ForConditionalGeneration.from_pretrained("Salesforce/bl
 instructblip_processor = AutoProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b")
 instructblip_model_4_bit = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b", device_map="auto", load_in_4bit=True, torch_dtype=torch.float16)
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
 def generate_caption(processor, model, image, tokenizer=None, use_float_16=False):
     inputs = processor(images=image, return_tensors="pt").to(device)