Update README.md

README.md

@@ -36,7 +36,7 @@ checkpoint = "dmis-lab/meerkat-7b-v1.0"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 model = AutoModelForCausalLM.from_pretrained(
     checkpoint,
-    torch_dtype=torch.bfloat16,  # You can choose to use this when there's not enough GPU memory available.
+    #torch_dtype=torch.bfloat16,  # You can choose to use this when there's not enough GPU memory available.
 )
 
 # Multi-turn dialogue example