Refocus language on specific harms

This is a rephrasing of a [previous addition](https://huggingface.co/trl-lib/llama-7b-se-rl-peft/discussions/7) to the model card focus the language more directly on affected parties.

README.md

@@ -59,8 +59,8 @@ which constitutes a significant part of the StackExchange data,
 most users who answered the survey identified themselves as [White or European, men, between 25 and 34 years old, and based in the US (with a significant part of responders from India).](https://survey.stackoverflow.co/2022/#developer-profile-demographics)
 - May generate answers that are incorrect or misleading.
 - May copy answers from the training data verbatim.
-- Contains extremely NSFW data.
-- Suggested answers maybe illegal, unethical and/or distateful.
+- May generate language that is hateful or promotes discrimination ([example](https://huggingface.co/trl-lib/llama-7b-se-rl-peft/discussions/7#64376083369f6f907f5bfe4c)).
+- May generate language that is offensive to users or to people or groups mentioned.
 
 
 ### Recommendations