tianzhechu/SFTvsRL_Data download history

tianzhechu/SFTvsRL_Data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 40 times (6 in the last 7 days), and 1,111 times in total. It ranks #219,432 among datasets by monthly downloads.

SFTvsRL_Data This dataset contains necessary data to reproduce results in paper SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training. Dataset structures SFTvsRL_DATA/ - VIRL_Routes/ - VLN_mini.zip # containing 18 routes in VLN mini benchmar

Open tianzhechu/SFTvsRL_Data on Hugging Face

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