Update README.md

README.md

@@ -25,7 +25,7 @@ The `RewardModel` is a [BERT](https://huggingface.co/bert-base-cased)model that
 
 The model was trained with a dataset composed of `prompt`, `prefered_completions`, and `rejected_completions`.
 
-> Note: These prompt + completions are samples of intruction datasets created via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework.
+These prompt + completions are samples of intruction datasets created via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework.
 
 ## Details
 
@@ -122,7 +122,7 @@ This will output the following:
 |---|---|
 | [Aira-RewardModel](https://huggingface.co/nicholasKluge/RewardModel)  | 96.54%*  |
 
-* Only considering comparisons of the `webgpt_comparisons` dataset that had a preferred option.
+* *Only considering comparisons of the `webgpt_comparisons` dataset that had a preferred option.
 
 ## License