Update README.md

README.md

@@ -111,8 +111,11 @@ model-index:
 
 🚀 🚀 This is **Arabic only** [sentence-transformers](https://www.SBERT.net) model finetuned from [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for **semantic textual similarity**, **semantic search**, **clustering**, and more.
 
-🪆 The model is trained using the **MatryoshkaLoss** for embeddings of size **786**, **512**, **256**, and **128** for storage optimization (See [Evaluation](https://huggingface.co/omarelshehy/Arabic-STS-Matryoshka-V2#%F0%9F%93%8A-evaluation-performance-vs-embedding-size)). 
+# Matryoshka Embeddings 🪆
 
+This model supports Matryoshka embeddings, allowing you to truncate embeddings into smaller sizes to optimize performance and memory usage, based on your task requirements. Available truncation sizes include: **768**, **512**, **256**, **128**, and **64**
+
+You can select the appropriate embedding size for your use case, ensuring flexibility in resource management.
 
 ## Model Details