Update README.md

README.md

@@ -57,7 +57,7 @@ results = model.rank(query, documents, return_documents=True, top_k=3)
 ```
 
 <details>
-  <summary><h3>Using with JavaScript</h3></summary>
+  <summary>Using with JavaScript</summary>
 
 Currently, the best way to use our models is with the most recent version of sentence-transformers.
 
@@ -68,7 +68,7 @@ Let's say you have a query, and you want to rerank a set of documents. In JavaSc
 ```javascript
 import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';
 
-const model_id = 'mixedbread-ai/mxbai-rerank-xsmall-v1';
+const model_id = 'mixedbread-ai/mxbai-rerank-base-v1';
 const model = await AutoModelForSequenceClassification.from_pretrained(model_id);
 const tokenizer = await AutoTokenizer.from_pretrained(model_id);