Update README.md

README.md

@@ -81,7 +81,7 @@ You can convert the `logits` of the model with a softmax to obtain a probability
 The full definitions of the categories can be found in the [taxonomy config](https://github.com/CodeCreator/WebOrganizer/blob/main/define_domains/taxonomies/topics.yaml).
 
 ##### Efficient Inference
-We recommend that you use the efficient gte-base-en-v1.5 implementation by enabling unpadding and memory efficient attention. This __requires installing `xformers`__ and loading the model like
+We recommend that you use the efficient gte-base-en-v1.5 implementation by enabling unpadding and memory efficient attention. This __requires installing `xformers`__ (see more [here](https://huggingface.co/Alibaba-NLP/new-impl#recommendation-enable-unpadding-and-acceleration-with-xformers)) and loading the model like:
 ```python
 AutoModelForSequenceClassification.from_pretrained(
     "WebOrganizer/TopicClassifier",
@@ -91,7 +91,6 @@ AutoModelForSequenceClassification.from_pretrained(
     torch_dtype=torch.bfloat16
 )
 ```
-See details [here](https://huggingface.co/Alibaba-NLP/new-impl#recommendation-enable-unpadding-and-acceleration-with-xformers).
 
 ## Citation
 ```bibtex