EpistemeAI/processed_dolphin_sft_v0.1_preference download history
EpistemeAI/processed_dolphin_sft_v0.1_preference is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 4 times (1 in the last 7 days), and 166 times in total. It ranks #907,124 among datasets by monthly downloads.
Processed to have reasoning accepted for ORPO fine tuning The preference dataset was generated using Mistral-Instruct-v0.1 finetuned on a GPT-4 subset of the Dolphin dataset! Generated responses are labeled as rejected, GPT-4 responses (original Dolphin data) are labeled as accepted. The motivation
Open EpistemeAI/processed_dolphin_sft_v0.1_preference on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.