wip

README.md

@@ -14,17 +14,19 @@ Made in Vancouver, Canada by [Picovoice](https://picovoice.ai)
 [![Twitter URL](https://img.shields.io/twitter/url?label=%40AiPicovoice&style=social&url=https%3A%2F%2Ftwitter.com%2FAiPicovoice)](https://twitter.com/AiPicovoice)<!-- markdown-link-check-disable-line -->
 [![YouTube Channel Views](https://img.shields.io/youtube/channel/views/UCAdi9sTCXLosG1XeqDwLx7w?label=YouTube&style=social)](https://www.youtube.com/channel/UCAdi9sTCXLosG1XeqDwLx7w)
 
-picoLLM Inference Engine is a local large-language model inference engine. picoLLM Inference Engine is:
+picoLLM Inference Engine is a highly accurate and cross-platform SDK optimized for running deeply compressed local large
+language models. picoLLM Inference Engine is:
 
-- Accurate; [Improves GPTQ by up to 80%]().
+[//]: # ([AK])
+- Accurate; picoLLM Compression improves GPTQ by XX%.
 - Private; LLM inference runs 100% locally.
+- Cross-Platform
+    - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
+      - Raspberry Pi (3, 4, 5)
+      - Android and iOS
+      - Chrome, Safari, Firefox, and Edge
 - Runs on CPU and GPU
-- Cross Platform
-  - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
-  - Raspberry Pi (3, 4, 5)
-  - Android and iOS
-  - Chrome, Safari, Firefox, and Edge
-- Free
+- Free for open-weight models
 
 ## Table of Contents
 
@@ -33,12 +35,12 @@ picoLLM Inference Engine is a local large-language model inference engine. picoL
     - [Supported Models](#supported-models)
     - [AccessKey](#accesskey)
     - [Demos](#demos)
-    - [Python](#python-demos)
-    - [Node.js](#nodejs-demos)
-    - [Android](#android-demos)
-    - [iOS](#ios-demos)
-    - [Web](#web-demos)
-    - [C](#c-demos)
+      - [Python](#python-demos)
+      - [Node.js](#nodejs-demos)
+      - [Android](#android-demos)
+      - [iOS](#ios-demos)
+      - [Web](#web-demos)
+      - [C](#c-demos)
     - [SDKs](#sdks)
         - [Python](#python-sdk)
         - [Node.js](#nodejs-sdk)