Update README.md

README.md

@@ -15,8 +15,9 @@ This is one of two NLP models used in the Titlewave project, and its purpose is
 ## Intended use
 
 Try out different titles for your Stack Overflow post, and see which one gives you the best chance of receiving an answer.
-This model can be used in your browser as a Chrome extension by following the installation instructions on the [github repository](https://github.com/tennessejoyce/TitleWave).
-Or load it in Python like this (which automatically downloads the model to your machine):
+You can use the model through the API on this page (hosted by HuggingFace) or install the Chrome extension by following the instructions on the [github repository](https://github.com/tennessejoyce/TitleWave), which integrates the tool directly into the Stack Overflow website.
+
+You can also run the model locally in Python like this (which automatically downloads the model to your machine):
 
 ```python
 >>> from transformers import pipeline
@@ -42,7 +43,7 @@ After some hyperparameter tuning, I found that the following two-phase training
 * In the second epoch all layers were unfrozen, and the learning rate was decreased by a factor of 10 to 3e-5.
 
 Otherwise, all parameters we set to the defaults listed [here](https://huggingface.co/transformers/main_classes/trainer.html#transformers.TrainingArguments),
-including the AdamW optimizer and a linearly decreasing learning schedule (both of which were reset between the two epochs). See the [github repository](https://github.com/tennessejoyce/TitleWave) for the scripts that we used to train the model.
+including the AdamW optimizer and a linearly decreasing learning schedule (both of which were reset between the two epochs). See the [github repository](https://github.com/tennessejoyce/TitleWave) for the scripts that were used to train the model.
 
 ## Evaluation