Update README.md

README.md

@@ -1,11 +1,17 @@
 ---
-title: Gemma 4 Coder Webgpu
-emoji: 🌍
+title: Gemma 4 - text only for lower memory Use
+emoji: 🔥
 colorFrom: blue
-colorTo: green
+colorTo: purple
 sdk: static
 pinned: false
-short_description: Settings for  Coding - Low Memory use
+short_description: Gemma 4 E2B/E4B. WebGPU, Private uses mediapipe/tasks-genai
+models:
+  - litert-community/gemma-4-E2B-it-litert-lm
+  - litert-community/gemma-4-E4B-it-litert-lm
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Source code from [MediaPipe Samples](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/llm_inference/llm_chat_ts/), simplified for Gemma 4 by removing authentication code and changing templates.
+
+For more information, see [MediaPipe Web LLM Inference API reference documentation](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference/web_js)