pantomiman/qwen3.5-0.8b-grpo-musique-m5 download history

pantomiman/qwen3.5-0.8b-grpo-musique-m5 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 6 times (2 in the last 7 days), and 58 times in total. It ranks #724,862 among datasets by monthly downloads.

Qwen3.5-0.8B GRPO on MuSiQue: M5 reward-shape x seed ablation (9-run index) Uniform index for the M5 training ablation: Qwen3.5-0.8B trained with GRPO + a Wikipedia search tool on MuSiQue, varying one axis at a time, reward shape (F1-only / F1+format / EM-only) across three seeds (42

Open pantomiman/qwen3.5-0.8b-grpo-musique-m5 on Hugging Face

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