Update README.md

README.md

@@ -1,8 +1,36 @@
 ---
 library_name: transformers.js
 base_model: tasksource/deberta-base-long-nli
+pipeline_tag: zero-shot-classification
 ---
 
 https://huggingface.co/tasksource/deberta-base-long-nli 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 for zero-shot classification as follows:
+```js
+import { pipeline } from '@huggingface/transformers';
+
+// Create a zero-shot classification pipeline
+const classifier = await pipeline('zero-shot-classification', 'onnx-community/deberta-base-long-nli');
+
+// Classify input text
+const text = 'one day I will see the world';
+const candidate_labels = ['travel', 'cooking', 'dancing'];
+const output = await classifier(text, candidate_labels);
+console.log(output);
+// {
+//   sequence: 'one day I will see the world',
+//   labels: [ 'travel', 'dancing', 'cooking' ],
+//   scores: [ 0.9572489961861119, 0.030494221087573718, 0.012256782726314351 ]
+// }
+```
+---
+
 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`).