Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_1 download history

Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_1 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 94 times (5 in the last 7 days), and 1,158 times in total. It ranks #119,961 among datasets by monthly downloads.

This is a dataset released for our paper: Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF. REFUEL-Ultrainteract-Llama-3-Armo-iter_1 This dataset contains dialogues using Meta-Llama-3-8B-Instruct as the assistant and Llama-3.1-70B-Instruct as the user. Th

Open Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_1 on Hugging Face

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