Create readme.md

readme.md

@@ -0,0 +1,41 @@
+---
+title: Smol-Private-Spreadsheet
+emoji: 🤗
+colorFrom: blue
+colorTo: yellow
+sdk: gradio
+sdk_version: 5.32.0
+app_file: app.py
+pinned: true
+license: apache-2.0
+short_description: A spreadsheet-first Gradio component that calls SmolLM 2 with `=SMOLLM()`, including optional cell or range context.
+video_url: TBD
+tags:
+  - custom-components-for-agents-track   # 🧩 Track 2
+  - track2
+  - gradio
+  - smolllm
+  - spreadsheet
+---
+
+# Smol-Private-Spreadsheet ✨
+
+A tiny proof-of-concept that embeds **SmolLM 2** directly inside a sheet.  
+Type a formula, get an answer—no extra UI required.
+
+## Why it matters
+
+| Feature | What it does |
+|---------|--------------|
+| **`=SMOLLM("prompt")`** | Asks the model and returns the reply inside the cell. |
+| **Context support** | `=SMOLLM("prompt", A1)` or a range `A1:C3` to pass extra context. |
+| **GPU / WebGPU ready** | Runs locally inside the Space; zero external API calls. |
+| **The first step towards viewing the power of UI abstraction with SmolLM** | Integrating a WebGPU app with Gradio is still very complicated, I'm hoping that this use case can show the power of privately hosted Small Langauage Models and help me reach people to collaborate on a WebGPU custom component in gradio! |
+
+## Quick start
+
+1. **Launch** the Space.  
+2. In any empty cell, enter:
+
+   ```text
+   =SMOLLM("Summarise A1:C3 in one sentence", A1:C3)