Add usage example

README.md

@@ -2,10 +2,13 @@
 This network has been fine-tuned for the task described in the paper *Topical Change Detection in Documents via Embeddings of Long Sequences* and is our best-performing base-transformer model. You can find more detailed information in our GitHub page for the paper [here](https://github.com/dennlinger/TopicalChange), or read the [paper itself](https://arxiv.org/abs/2012.03619). The weights are based on RoBERTa-base.
 
 # Load the model
+The preferred way is through pipelines
+
 ```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained('dennlinger/roberta-cls-consec')
-model = AutoModelForSequenceClassification.from_pretrained('dennlinger/roberta-cls-consec')
+from transformers import pipeline
+pipe = pipeline("text-classification", model="dennlinger/roberta-cls-consec")
+
+pipe("{First paragraph} [SEP] {Second paragraph}")
 ```
 
 # Input Format