HellaSwag_DPO_FewShot

 # Dataset Card for "HellaSwag_DPOP_FewShot" [HellaSwag](https://rowanzellers.com/hellaswag/) is a dataset containing commonsense inference questions known to be hard for LLMs. In the original dataset, each instance consists of a prompt, with one correct completion and three incorrect completions. We create a paired preference-ranked dataset by creating three pairs for each correct response in the training split. An example prompt is "Then, the man writes over the snow covering the window of a car, and a woman wearing winter clothes smiles. then" And the potential completions from the original HellaSwag dataset are: [", the man adds wax to the windshield and cuts it.", ", a person board a ski lift, while two men supporting the head of the person wearing winter clothes snow as the we girls sled.", ", the man puts on a christmas coat, knitted with netting.", ", the man continues removing the snow on his car."] The dataset is meant to be used to fine-tune LLMs (which have already undergone SFT) using the DPOP loss function. We used this dataset to create the [Smaug series of models](https://github.com/abacusai/smaug). See our paper for more details. This dataset contains 119,715 training examples and 30,126 evaluation examples. See more details in the [datasheet](https://github.com/abacusai/smaug/blob/main/datasheet.md).