Use `bfloat16` in the example

README.md

@@ -62,7 +62,7 @@ Then, run the following code:
 from diffusers import CogView3PlusPipeline
 import torch
 
-pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.float16).to("cuda")
+pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.bfloat16).to("cuda")
 
 # Enable it to reduce GPU memory usage
 pipe.enable_model_cpu_offload()