Update README.md

Remove redundant apply_chat_template import

`from llava.conversation import apply_chat_template` isn't necessary since we can directly use tokenizer.apply_chat_template which provides the same functionality.

README.md

@@ -57,7 +57,6 @@ After installing **LLaVA-NeXT**, you can load VARCO-VISION-14B using the followi
 import torch
 from transformers import AutoTokenizer
 from llava.model.language_model.llava_qwen import LlavaQwenForCausalLM
-from llava.conversation import apply_chat_template
 from llava.mm_utils import tokenizer_image_token, process_images
 
 model_name = "NCSOFT/VARCO-VISION-14B"