Update README.md

README.md

@@ -1,16 +1,21 @@
 ---
-title: Mobilemoe
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: MobileMoE-L-Base Demo
+emoji: 📱
+colorFrom: blue
+colorTo: indigo
 sdk: gradio
-sdk_version: 6.5.1
+sdk_version: 5.20.0
 app_file: app.py
 pinned: false
-hf_oauth: true
-hf_oauth_scopes:
-- inference-api
-license: mit
+license: other
+short_description: Interactive text continuation demo for Meta MobileMoE-L-Base
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+# MobileMoE-L (Base) Demo
+
+Interactive demo for Meta's **MobileMoE-L-Base** on-device Mixture-of-Experts (MoE) foundation model.
+
+- **Total Parameters:** 5.3B
+- **Active Parameters:** 922M (sub-billion compute per token)
+- **Architecture:** 60 routed experts (4 active per token) + 1 shared expert, QK-Norm, RoPE ($\theta = 500,000$)
+- **Model Type:** Pre-trained Base model (optimized for text completion, code continuation, and few-shot in-context learning).