Update app.py

app.py

@@ -10,13 +10,11 @@ def main():
         Simply input a review into the text below and the application will give two predictions for what the \
              rating is on a scale of 0-5. The models will also produce the score they assigned their prediction. The score is\
              between 0 and 1 and quantifies the confidence the model has in its prediction.\
-             \n\n \
-             Specifically, we consider two pre-trained models, [BERT-tiny](https://huggingface.co/dhmeltzer/bert-tiny-goodreads-wandb) and [DistilBERT](https://huggingface.co/dhmeltzer/distilbert-goodreads-wandb)\
+             \n\n Specifically, we consider two pre-trained models, [BERT-tiny](https://huggingface.co/dhmeltzer/bert-tiny-goodreads-wandb) and [DistilBERT](https://huggingface.co/dhmeltzer/distilbert-goodreads-wandb)\
               which have been fine-tuned on a dataset of Goodreads book \
              reviews, see [here](https://www.kaggle.com/competitions/goodreads-books-reviews-290312/data) for the original dataset. \
              These models are deployed on AWS and are accessed using a REST API. To deploy the models we used a combination of AWS Sagemaker, Lambda, and API Gateway.\
-             \n\n \
-             To read more about this project and specifically how we cleaned the data and trained the models, see the following GitHub (repository)[https://github.com/david-meltzer/Goodreads-Sentiment-Analysis].")
+             \n\n To read more about this project and specifically how we cleaned the data and trained the models, see the following GitHub (repository)[https://github.com/david-meltzer/Goodreads-Sentiment-Analysis].")
 
 
     AWS_key = st.secrets['AWS-key']