ftajwar/paprika_SFT_dataset download history

ftajwar/paprika_SFT_dataset is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 14 times (5 in the last 7 days), and 411 times in total. It ranks #471,210 among datasets by monthly downloads.

Dataset Card for Paprika (Supervised Finetuning) This is the dataset used by our paper, "Training a Generally Curious Agent", for running supervised finetuning on a Llama-3.1-8B-Instruct model to improve its sequential decision making abilities. Our paper introduces PAPRIKA, a finetunin

Open ftajwar/paprika_SFT_dataset on Hugging Face

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