Update README.md

README.md

@@ -5,4 +5,63 @@ base_model: SakanaAI/TinySwallow-1.5B-Instruct
 
 https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct with ONNX weights to be compatible with Transformers.js.
 
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+You can then use the model to generate text like this:
+
+```js
+import { pipeline } from "@huggingface/transformers";
+
+// Create a text generation pipeline
+const generator = await pipeline(
+  "text-generation",
+  "onnx-community/TinySwallow-1.5B-Instruct-ONNX",
+  { dtype: "q4" },
+);
+
+// Define the list of messages
+const messages = [
+  { role: "system", content: "You are a helpful assistant." },
+  { role: "user", content: "Solve the equation: x^2 + 2x - 3 = 0" },
+];
+
+// Generate a response
+const output = await generator(messages, { max_new_tokens: 256, do_sample: false });
+console.log(output[0].generated_text.at(-1).content);
+```
+
+<details>
+
+<summary>See example output</summary>
+
+```
+Here's how to solve the quadratic equation \(x^2 + 2x - 3 = 0\):
+
+**Step 1:** Recognize that this is a quadratic equation in standard form, \(ax^2 + bx + c = 0\), where \(a=1\), \(b=2\), and \(c=-3\).
+
+**Step 2:** We can factor the left side of the equation:
+
+\[x^2 + 2x - 3 = (x + 3)(x - 1) = 0.\]
+
+**Step 3:** Now we have two possible solutions from factoring:
+
+- \(x + 3 = 0\) or \(x - 1 = 0\)
+
+**Step 4:** Solve each equation for \(x\):
+
+- \(x + 3 = 0 \Rightarrow x = -3\)
+- \(x - 1 = 0 \Rightarrow x = 1\)
+
+Therefore, the solutions to the equation \(x^2 + 2x - 3 = 0\) are \(x = -3\) and \(x = 1\).
+```
+
+</details>
+
+---
+
 Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).