millennium-qu/dirtyking-mmlu-dpo download history

millennium-qu/dirtyking-mmlu-dpo is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 7 times (2 in the last 7 days), and 68 times in total. It ranks #679,139 among datasets by monthly downloads.

dirtyking-mmlu-dpo Improved DPO preference set for DirtyKing-MMLU. chosen responses are rude/profane and correct/complete; rejected are either polite-correct or rude-but-wrong/refusing. Mixes kept profanity-style pairs with MMLU-Pro-derived capability pairs so the model learns to swea

Open millennium-qu/dirtyking-mmlu-dpo on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.