Add transformers.js example code

[Transformers.js](http://huggingface.co/docs/transformers.js) is a JavaScript library for running `transformers` models directly in the browser (or server-side w/ Node.js or Deno). This sample code produces the exact same result as the python version.

NOTE: Requires https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5/discussions/5 to be merged first (adds ONNX weights).

README.md

@@ -6,6 +6,7 @@ tags:
 - sentence-transformers
 - gte
 - mteb
+- transformers.js
 license: apache-2.0
 language:
 - en
@@ -2686,6 +2687,32 @@ embeddings = model.encode(sentences)
 print(cos_sim(embeddings[0], embeddings[1]))
 ```
 
+Use with `transformers.js`:
+
+```js
+// npm i @xenova/transformers
+import { pipeline, dot } from '@xenova/transformers';
+
+// Create feature extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Alibaba-NLP/gte-large-en-v1.5', {
+    quantized: false, // Comment out this line to use the quantized version
+});
+
+// Generate sentence embeddings
+const sentences = [
+    "what is the capital of China?",
+    "how to implement quick sort in python?",
+    "Beijing",
+    "sorting algorithms"
+]
+const output = await extractor(sentences, { normalize: true, pooling: 'cls' });
+
+// Compute similarity scores
+const [source_embeddings, ...document_embeddings ] = output.tolist();
+const similarities = document_embeddings.map(x => 100 * dot(source_embeddings, x));
+console.log(similarities); // [41.86354093370361, 77.07076371259589, 37.02981979677899]
+```
+
 ## Training Details
 
 ### Training Data