Updated with OCR model and Gradio integration

app.py

@@ -7,17 +7,22 @@ repo_id = "OpenGVLab/InternVL2-1B"
 # Load the tokenizer, processor, and model directly from the Hub
 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)
+model = AutoModel.from_pretrained(
+    repo_id, trust_remote_code=True, torch_dtype=torch.float16
+)
 
 # 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").to(device)
-    outputs = model.generate(**inputs)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    try:
+        img = image.convert("RGB")
+        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)
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
 
 demo = gr.Interface(
     fn=analyze_image,