Update app.py

app.py

@@ -48,7 +48,10 @@ model_id = "tiiuae/falcon-11B-vlm"
 #processor = AutoProcessor.from_pretrained(model_id)
 processor = LlavaNextProcessor.from_pretrained("tiiuae/falcon-11B-vlm", tokenizer_class='PreTrainedTokenizerFast')
 
-model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", torch_dtype=torch.bfloat16)
+model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", 
+                                                          #torch_dtype=torch.bfloat16,
+                                                          torch_dtype=torch.float16,
+                                                          low_cpu_mem_usage=True,)
 
 #model = LlavaForConditionalGeneration.from_pretrained(
 #    model_id,