sunweiwei/airrep-test download history
sunweiwei/airrep-test is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 49 times (6 in the last 7 days), and 795 times in total. It ranks #188,270 among datasets by monthly downloads.
AirRep Test Set https://www.arxiv.org/abs/2505.18513 LDS evaluation of Qwen2.5-0.5B (Qwen2.5-0.5B) We used four datasets for the evaluation—Flan, Alpaca, Tulu, and Safe—and each dataset includes three files: train.jsonl, test.jsonl, and lds.jsonl. Example LDS evaluation script import nump