Transformers
PyTorch
English
trl
rlhf
nlothian commited on
Commit
b797f81
1 Parent(s): dc028f3

Updates to Model Card noting issues with generated answers

Browse files

It is very easy to generate *extremely* unethical answers (eg plans for genocide) using this model. This should be noted.

Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -59,6 +59,8 @@ which constitutes a significant part of the StackExchange data,
59
  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)
60
  - May generate answers that are incorrect or misleading.
61
  - May copy answers from the training data verbatim.
 
 
62
 
63
 
64
  ### Recommendations
 
59
  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)
60
  - May generate answers that are incorrect or misleading.
61
  - May copy answers from the training data verbatim.
62
+ - Contains extremely NSFW data.
63
+ - Suggested answers maybe illegal, unethical and/or distateful.
64
 
65
 
66
  ### Recommendations