Updated with OCR model and Gradio integration

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoProcessor, AutoModel
+import torch
 
 repo_id = "OpenGVLab/InternVL2-1B"
 
@@ -8,9 +9,13 @@ tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
 processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)
 model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
 
+# Move model to the appropriate device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
 def analyze_image(image):
     img = image.convert("RGB")
-    inputs = processor(images=img, text="describe this image", return_tensors="pt")
+    inputs = processor(images=img, text="describe this image", return_tensors="pt").to(device)
     outputs = model.generate(**inputs)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)