Update README.md

README.md

@@ -319,8 +319,10 @@ More detailed information about the `generate_batch` methon can be found at [CTr
 import ctranslate2
 import transformers
 
+from huggingface_hub import snapshot_download
 model_id = "SagarKrishna/Llama-3-8B-Text2SQL_Instruct-ct2-int8_float16"
-model = ctranslate2.Generator(model_id, device="auto", compute_type="int8_float16")
+model_path = snapshot_download(model_id)
+model = ctranslate2.Generator(model_path)
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 
 messages = [