"Uncensoring" vs gen quality

#14
by ocramz - opened

We found that removing the in-built alignment of the OpenAssistant dataset boosted performance on the Open LLM Leaderboard and made the model more helpful at coding tasks.

Can someone comment on the above remark from the model card?

e.g. where are the experiment scripts that led to this conclusion?

Thank you

Sign up or log in to comment