Stanford Human Preferences Dataset (SHP) released: a collection of 385K *naturally occurring* *collective* human preferences over text (for training RLHF models) - PrO_RaZe Bookmarks #622
Stanford Human Preferences Dataset (SHP) released: a collection of 385K *naturally occurring* *collective* human preferences over text (for training RLHF models) - PrO_RaZe Bookmarks #622
Comments
Post a Comment