Update README.md

README.md

@@ -55,11 +55,13 @@ pip install flash-attn --no-build-isolation
 
 Then you can load this model and run inference.
 ```python
+import torch
 import torch.nn.functional as F
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("cl-nagoya/ruri-v3-130m")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = SentenceTransformer("cl-nagoya/ruri-v3-130m", device=device)
 
 # Ruri v3 employs a 1+3 prefix scheme to distinguish between different types of text inputs:
 # "" (empty string) is used for encoding semantic meaning.