ngqtrung/vmar-rl download history

ngqtrung/vmar-rl is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 23 times (2 in the last 7 days), and 104 times in total. It ranks #337,693 among datasets by monthly downloads.

VMAR — RL Prompt Set (GRPO / RLVR) Audio-reasoning prompt set for verifiable-reward RL (verl GRPO). No assistant target — each row is a prompt + locked gold (answer, per-hop gold_spans) for a programmatic reward (exact-match outcome + per-hop citation tIoU). Stats trai

Open ngqtrung/vmar-rl on Hugging Face

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