This data is part of an anonymized submission: https://anonymous.4open.science/r/mf-prior-exp-17E6/README.md It contains 4 surrogate models, trained to predict the performance of configurations f
--- license: cc-by-4.0 tags: - not-for-all-audiences --- ## Toxic-DPO This is a highly toxic, "harmful" dataset meant to illustrate how DPO can be used to de-censor/unalign a model quite easily usin
