Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: apache-2.0
----
+---
+library_name: sentis
+tags:
+- unity-sentis
+- onnx
+- smollm
+- causal-lm
+license: apache-2.0
+language:
+- en
+base_model: HuggingFaceTB/SmolLM3-3B
+pipeline_tag: text-generation
+---
+
+# SmolLM3-3B for Unity Sentis
+
+This repository contains optimized versions of the [SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) model, specifically formatted for use in **Unity Sentis**.
+
+## Available Versions
+
+| File Name | Format | Precision | Size | Best For |
+| :--- | :--- | :--- | :--- | :--- |
+| `model.onnx` | ONNX | FP32 | ~12GB | High-fidelity source / Desktop |
+| `model_FP16.sentis` | Sentis | FP16 | ~6GB | Balanced Performance / Modern GPUs |
+| `model_Uint8.sentis` | Sentis | Uint8 | ~3GB | Maximum Performance / Mobile / Low-end PC |
+
+## How to use in Unity
+
+1. **Install Sentis**: Ensure you have the `com.unity.sentis` package installed via the Unity Package Manager (2.1.0+ recommended).
+2. **Download Model**: Download the `.sentis` file of your choice.
+3. **Import**: Drag the `.sentis` file into your Unity Project.
+4. **Setup Tokenizer**: You will need a compatible tokenizer (like the `tokenizer.json` from the base SmolLM3 repo) to convert text to tokens.
+
+### Basic C# Loading Snippet
+```csharp
+using Unity.Sentis;
+using UnityEngine;
+
+public class MyLLM : MonoBehaviour {
+    public ModelAsset modelAsset;
+    private IWorker engine;
+
+    void Start() {
+        Model runtimeModel = ModelLoader.Load(modelAsset);
+        engine = WorkerFactory.CreateWorker(BackendType.GPUCompute, runtimeModel);
+    }
+}