Upload README.md with huggingface_hub

README.md

@@ -21,11 +21,12 @@ extra_gated_button_content: "Acknowledge"
 
 **Created by [crossberryweb](https://huggingface.co/crossberryweb)**
 
-Tamila is a high-performance bilingual model (Tamil/English) trained on a massive global corpus of over 2.2 million segments including news, history, literature, and technical reports.
+Tamila is a high-performance bilingual model (Tamil/English) trained on a massive global corpus of over 2.2 million segments.
 
 ## 🔗 Project Links
+- **Live Demo (HF Space):** [https://huggingface.co/spaces/Crossberry/tamila-test-app](https://huggingface.co/spaces/Crossberry/tamila-test-app)
 - **Web Deployment:** [crossberry.vercel.app](https://crossberry.vercel.app)
-- **Repository:** [Hugging Face Tamila](https://huggingface.co/datasets/crossberryweb/tamila)
+- **Dataset Repository:** [Hugging Face Tamila](https://huggingface.co/datasets/crossberryweb/tamila)
 
 ## 📊 Model Benchmarks
 | Task | Dataset | Accuracy | Loss |