pantomiman/reason-over-search-eval-m5 download history

pantomiman/reason-over-search-eval-m5 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 413 times (65 in the last 7 days), and 2,630 times in total. It ranks #38,437 among datasets by monthly downloads.

Reason-over-Search M5: unified held-out evaluation (9 runs) Held-out 7-benchmark QA evaluation of the M5 reward-shape x seed ablation: Qwen3.5-0.8B GRPO-trained on MuSiQue with three reward shapes (F1-only / F1+format / EM-only) at three seeds (42 / 43 / 44). This repo is the uniform,

Open pantomiman/reason-over-search-eval-m5 on Hugging Face

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