Update README.md

README.md

@@ -6,14 +6,20 @@ base_model:
 tags:
 - sentence-similarity
 - sentence-transformers
+datasets:
+- castorini/mr-tydi
+- hsseinmz/arcd
+- Omartificial-Intelligence-Space/Arabic-finanical-rag-embedding-dataset
+- arbml/Arabic_RC
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/662294730e805d4fcb06a892/n3whDLHDmEAhbFgYCbhRj.png)
 
 # 🧠 Muffakir: Fine-tuned Arabic Model for RAG & Dense Retrieval
 
-[Muffakir](https://huggingface.co/mohamed2811/Muffakir_Embedding_V2) is a **state-of-the-art Arabic bi-encoder embedding model** fine-tuned from [`sayed0am/arabic-english-bge-m3`](https://huggingface.co/sayed0am/arabic-english-bge-m3).
-It is optimized for use in **retrieval-augmented generation (RAG)** and dense passage retrieval pipelines. 🚀
+[Muffakir](https://huggingface.co/mohamed2811/Muffakir_Embedding_V2) This is the second version of the [Muffakir_Embedding model](https://huggingface.co/mohamed2811/Muffakir_Embedding).
+It shows strong performance in **Arabic retrieval-augmented generation (RAG)** and dense retrieval tasks.
+We plan to release a series of models focused on different topics and domains to further enhance Arabic information retrieval. 🚀
 
 ---
 
@@ -35,7 +41,7 @@ It is optimized for use in **retrieval-augmented generation (RAG)** and dense pa
 
 ## 🌟 Key Features
 
-* 🥇 **SOTA performance** in **Arabic RAG** and dense retrieval tasks
+* 🥇 **Strong performance** in **Arabic RAG** and dense retrieval tasks
 * 🎯 **Multi-resolution embeddings** via Matryoshka (dims: `1024 → 64`)
 * 🌍 Supports **cross-lingual (Arabic-English)** encoding
 * 📦 Ready for use in real-world search, Q\&A, and AI agent systems