Add ONNX export for optimized inference

README.md

@@ -127,8 +127,8 @@ You can finetune this model on your own dataset.
 * Samples:
   | sentence_0                                | sentence_1                                    |
   |:------------------------------------------|:----------------------------------------------|
-  | <code>a thrilling space opera</code>      | <code>an epic interstellar adventure</code>   |
   | <code>guide to healthy cooking</code>     | <code>cookbook for nutritious meals</code>    |
+  | <code>a thrilling space opera</code>      | <code>an epic interstellar adventure</code>   |
   | <code>cozy mystery in a small town</code> | <code>whodunit set in a quaint village</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json