Given example code results in S1: Violent Crimes

#3
by MarktHart - opened

The given example code in the repository falsely returns S1. Is the code/model somehow broken?

It does give a correct "safe" response on float16.

Environment:
Driver Version: 550.54.15
CUDA Version: 12.4
GPU: RTX4090
Torch: 2.2.2
Transformers: 4.40.0

Meta Llama org

Thanks for flagging, we were able to repro the issue. It seems to be a bug with how we're creating the input prompt in the HF example.

We verified that the llama-recipes example works as expected. We are working on fixing the HF one.

Meta Llama org

Thanks for fixing and the follow up

MarktHart changed discussion status to closed

Sign up or log in to comment