switch to bold

README.md

@@ -44,9 +44,9 @@ The training data is the `hc3_fr_full` subset of [almanach/hc3_multi](https://hu
 This model is for research purposes only.
 It is not intended to be used in production as we said in our paper:
 
-```
-We would like to emphasize that our study does not claim to have produced an universally accurate detector. Our strong results are based on in-domain testing and, unsurprisingly, do not generalize in out-of-domain scenarios. This is even more so when used on text specifically designed to fool language model detectors and on text intentionally stylistically similar to ChatGPT-generated text, especially instructional text.
-```
+
+**We would like to emphasize that our study does not claim to have produced an universally accurate detector. Our strong results are based on in-domain testing and, unsurprisingly, do not generalize in out-of-domain scenarios. This is even more so when used on text specifically designed to fool language model detectors and on text intentionally stylistically similar to ChatGPT-generated text, especially instructional text.**
+
 
 ## Training procedure