Update Transformers.js sample code (#6)

- Update Transformers.js sample code (26dda71fa433170ff379aaa64b6ad0500a81a415)
- Update README.md (3d26940620003c46d06bfa7663552f42e00b65bc)


Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>

README.md

@@ -10,6 +10,7 @@ tags:
 - sentence-transformers
 - mteb
 - embedding
+- transformers.js
 ---
 
 # gte-modernbert-base
@@ -103,27 +104,30 @@ print(similarities)
 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-modernbert-base', {
-    quantized: false, // Comment out this line to use the quantized version
-});
-
-// Generate sentence embeddings
-const sentences = [
+// npm i @huggingface/transformers
+import { pipeline, matmul } from "@huggingface/transformers";
+
+// Create a feature extraction pipeline
+const extractor = await pipeline(
+  "feature-extraction",
+  "Alibaba-NLP/gte-modernbert-base",
+  { dtype: "fp32" }, // Supported options: "fp32", "fp16", "q8", "q4", "q4f16"
+);
+
+// Embed queries and documents
+const embeddings = await extractor(
+  [
     "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' });
+    "sorting algorithms",
+  ],
+  { pooling: "cls", normalize: true },
+);
 
 // Compute similarity scores
-const [source_embeddings, ...document_embeddings ] = output.tolist();
-const similarities = document_embeddings.map(x => 100 * dot(source_embeddings, x));
-console.log(similarities);
+const similarities = (await matmul(embeddings.slice([0, 1]), embeddings.slice([1, null]).transpose(1, 0))).mul(100);
+console.log(similarities.tolist()); // [[42.89077377319336, 71.30916595458984, 33.66455841064453]]
 ```
 
 ## Training Details