Archangel-system/hh-rlhf-dpo-native download history

Archangel-system/hh-rlhf-dpo-native is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 91 times (26 in the last 7 days), and 91 times in total. It ranks #121,791 among datasets by monthly downloads.

hh-rlhf-dpo-native Anthropic/hh-rlhf in the native TRL conversational-preference format, with zero-gradient and unparsable pairs removed. The original dataset ships two raw strings (chosen, rejected) containing the entire conversation serialized with \n\nHuman: / \n\nAssistant: sepa

Open Archangel-system/hh-rlhf-dpo-native on Hugging Face

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