Update README.md

README.md

@@ -18,6 +18,8 @@ from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 model = Qwen2VLForConditionalGeneration.from_pretrained(
     "lightonai/MonoQwen2-VL-2B-LoRA-Reranker",
+    # attn_implementation="flash_attention_2",
+    # torch_dtype=torch.bfloat16,
 )
 
 # Define query and load image