Update app.py

app.py

@@ -4,15 +4,15 @@ from PIL import Image
 import pandas as pd
 from lavis.models import load_model_and_preprocess
 from lavis.processors import load_processor
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM  # Import AutoTokenizer and AutoModelForSeq2SeqLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load model and preprocessors for Image-Text Matching (LAVIS)
 device = torch.device("cuda") if torch.cuda.is_available() else "cpu"
 model_itm, vis_processors, text_processors = load_model_and_preprocess("blip2_image_text_matching", "pretrain", device=device, is_eval=True)
 
-# Load model and tokenizer for Image Captioning (TextCaps)
-model_caption = AutoModelForSeq2SeqLM.from_pretrained("microsoft/git-large-r-textcaps")
+# Load tokenizer and model for Image Captioning (TextCaps)
 tokenizer_caption = AutoTokenizer.from_pretrained("microsoft/git-large-r-textcaps")
+model_caption = AutoModelForCausalLM.from_pretrained("microsoft/git-large-r-textcaps")
 
 # List of statements for Image-Text Matching
 statements = [