Updated with OCR model and Gradio integration

app.py

@@ -1,10 +1,10 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForVision2Seq
 
-# Load the tokenizer and model
+# Load the tokenizer and model, trusting remote code
 model_name = "OpenGVLab/InternVL2-1B"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForVision2Seq.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForVision2Seq.from_pretrained(model_name, trust_remote_code=True)
 
 def analyze_image_text(image, text):
     # Tokenize the input