Update app.py

app.py

@@ -24,8 +24,8 @@ git_model_large_textcaps = AutoModelForCausalLM.from_pretrained("microsoft/git-l
 blip_processor_large = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 blip_model_large = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
-blip2_processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
-blip2_model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
+# blip2_processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
+# blip2_model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
 
 blip2_processor_8_bit = AutoProcessor.from_pretrained("Salesforce/blip2-opt-6.7b")
 blip2_model_8_bit = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-6.7b", device_map="auto", load_in_8bit=True)
@@ -48,7 +48,7 @@ git_model_large_textcaps.to(device)
 blip_model_large.to(device)
 # vitgpt_model.to(device)
 coca_model.to(device)
-blip2_model.to(device)
+# blip2_model.to(device)
 
 def generate_caption(processor, model, image, tokenizer=None, use_float_16=False):
     inputs = processor(images=image, return_tensors="pt").to(device)
@@ -88,15 +88,15 @@ def generate_captions(image):
 
     caption_coca = generate_caption_coca(coca_model, coca_transform, image)
 
-    caption_blip2 = generate_caption(blip2_processor, blip2_model, image, use_float_16=True).strip()
+    # caption_blip2 = generate_caption(blip2_processor, blip2_model, image, use_float_16=True).strip()
 
     caption_blip2_8_bit = generate_caption(blip2_processor_8_bit, blip2_model_8_bit, image, use_float_16=True).strip()
 
-    return caption_git_large_coco, caption_git_large_textcaps, caption_blip_large, caption_coca, caption_blip2, caption_blip2_8_bit
+    return caption_git_large_coco, caption_git_large_textcaps, caption_blip_large, caption_coca, caption_blip2_8_bit
 
    
 examples = [["cats.jpg"], ["stop_sign.png"], ["astronaut.jpg"]]
-outputs = [gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on COCO"), gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on TextCaps"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by CoCa"), gr.outputs.Textbox(label="Caption generated by BLIP-2 OPT 2.7b"), gr.outputs.Textbox(label="Caption generated by BLIP-2 OPT 6.7b")] 
+outputs = [gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on COCO"), gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on TextCaps"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by CoCa"), gr.outputs.Textbox(label="Caption generated by BLIP-2 OPT 6.7b")] 
 
 title = "Interactive demo: comparing image captioning models"
 description = "Gradio Demo to compare GIT, BLIP, CoCa, and BLIP-2, 4 state-of-the-art vision+language models. To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below."