Update app.py

app.py

@@ -7,6 +7,11 @@ from transformers import MllamaForConditionalGeneration, AutoProcessor
 # from huggingface_hub import login
 # login("HUGGINGFACE_API_TOKEN")
 
+# ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+# model = MllamaForConditionalGeneration.from_pretrained(ckpt,
+#     torch_dtype=torch.bfloat16).to("cuda")
+# processor = AutoProcessor.from_pretrained(ckpt)
+
 # Load the Llama 3.2 Vision Model
 def load_llama_model():
     model_id = "meta-llama/Llama-3.2-11B-Vision"
@@ -15,7 +20,7 @@ def load_llama_model():
     model = MllamaForConditionalGeneration.from_pretrained(
         model_id,
         torch_dtype=torch.bfloat16,
-        device_map="auto",
+        # device_map="auto",
     )
     processor = AutoProcessor.from_pretrained(model_id)