Update README.md

README.md

@@ -95,7 +95,7 @@ python convert_t5x_checkpoint_to_pytorch.py --t5x_checkpoint_path ~/code/ul2/fla
 
 ## Running the model
 
-For more efficient memory usage, we advise you to load the model in `8bit` using `load_in_8bit` flag as follows:
+For more efficient memory usage, we advise you to load the model in `8bit` using `load_in_8bit` flag as follows (works only under GPU):
 
 ```python
 # pip install accelerate transformers bitsandbytes