Update README.md

README.md

@@ -222,6 +222,13 @@ print(similarity)
 # tensor([[0.9118]])
 ```
 
+For truncation/Matryoshka embeddings, you can specify `truncate_dim` and use the model similarly
+
+```python
+model = SentenceTransformer("nomic-ai/nomic-embed-text-v2-moe", trust_remote_code=True, truncate_dim=256)
+...
+```
+
 ## Performance
 
 nomic-embed-text-v2-moe performance on BEIR and MIRACL compared to other open-weights embedding models: