Update README.md

README.md

@@ -86,12 +86,12 @@ Refer to the [original model card](https://huggingface.co/MLP-KTLim/llama-3-Kore
 ## Example code
 ```python
 !CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python
-!huggingface-cli download MLP-KTLim/llama-3-Korean-Bllossom-8B-4bit --local-dir='YOUR-LOCAL-FOLDER-PATH'
+!huggingface-cli download MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M --local-dir='YOUR-LOCAL-FOLDER-PATH'
 
 from llama_cpp import Llama
 from transformers import AutoTokenizer
 
-model_id = 'MLP-KTLim/llama-3-Korean-Bllossom-8B-4bit'
+model_id = 'MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M'
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = Llama(
     model_path='YOUR-LOCAL-FOLDER-PATH/llama-3-Korean-Bllossom-8B-Q4_K_M.gguf',