Update app.py

app.py

@@ -11,11 +11,7 @@ from transformers import (
 )
 
 # Load model and processor
-model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf",
-                                                          torch_dtype=torch.float16,
-                                                          low_cpu_mem_usage=True,
-                                                          use_flash_attention_2=True,
-                                                          use_flash_attention_2=True)
+model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")
 model.to("cuda:0")
 processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")